025DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The information disclosure statement(s) (IDS) submitted on 01/22/2025 have been considered and placed in the applicant file.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier.
Claims 1, 4, and 13-18, recites limitations that use words like “means” (or “step”) or similar terms with functional language and do invoke 35 U.S.C. 112(f):
Claim 1; recites the limitation, “a scanner configured to...” [Line 2].
Claim 1 and 5; recites the limitation, “a data processor configured to...” [Line 4; Line 1].
Claim 1; recites the limitation, “an object identifier configured to...” [Line 6].
Claim 1, 12, 14 and 15; recites the limitation, “a welding determiner configured to…” [Line 8; Line 3; Line 1-2; and Line 1-2].
Because these claim limitation(s) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, they are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
After a careful analysis, as disclosed above, and a careful review of the specification the following limitations in claims 1, 5, 12, 14 and 15:
(i) “a scanner” (Fig. 1, #110. Paragraph [0044 and 0047]-the scanner 110 is described as an optical scanner for acquiring the two-dimensional image and/or the three-dimensional image. Fig. 1, illustrates the scanner 110 as a black box connected to the processor 120 (wherein the scanner 110 has sufficient structure and is understood as an optical scanner)).
(ii) “a data processor” (Fig. 1, #121. Paragraph [0044 and 0048]-the data processor 121 is described as generating fusion data (or a fusion image) based on the two-dimensional image and the three-dimensional image (S130). Fig. 1, illustrates data processor 121 as a black box enclosed within a processor 120 (wherein the data processor 121 has sufficient structure associated with it and is understood as a processor)).
(iii) “an object identifier” (Fig. 1, #123. Paragraph [0044]-the object identifier 123 is described as identifying a welding area from the fusion data based on an artificial intelligence (AI) model. Fig. 1, illustrates an object identifier 123 as a black box enclosed within a processor 120 (wherein the object identifier 123 has sufficient structure associated with it and is understood as a processor)).
(iv) “a welding determiner” (Fig. 1, #125. Paragraph [0044]-the object identifier 123 is described as identifying a welding area from the fusion data based on an artificial intelligence (AI) model. Fig. 1, illustrates an object identifier 123 as a black box enclosed within a processor 120 (wherein the object identifier 123 has sufficient structure associated with it and is understood as a processor)).
If applicant does not intend to have these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-2, 4-7, 12, 14-16 and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over JIANG et al. (US 20230281919 A1), hereinafter referenced as JIANG in view of PAN et al. (PAN YONG et al., Machine Translation of Patent Publication CN116051542A, "Defect detection method and defect detection device"), hereinafter referenced as PAN.
Regarding claim 1, JIANG explicitly teaches a welding inspection apparatus (Fig. 4. Paragraph [0061]-JIANG discloses FIG. 4 illustrates a flowchart of an appearance detection method. In paragraph [0038]-JIANG discloses a fourth aspect of the present application provides a non-transitory storage medium storing instructions when executed by a processor, cause the processor to perform the appearance detection method. In paragraph [0060]-JIANG discloses FIGS. 3a to 3d illustrate an embodiment of welding defect detection of a lithium battery sealing pin. Please also see Fig. 1-3 and read paragraph [0050]) comprising:
a scanner configured to acquire a two-dimensional image (Fig. 2. Paragraph [0053]-JIANG discloses FIG. 2 illustrates a flowchart of an image processing method. In paragraph [0054]-JIANG discloses in step 204, a two-dimensional image of the object. Then, in step 208, the two-dimensional color image with three (RGB) channels is grayed by weighting to obtain a single-channel grayscale image (wherein a single channel grayscale image may be obtained using the following equation: p=w.sub.1R+w.sub.2G+w.sub.3B, where p represents a grayscale value of a coordinate point, R represents a red value of the coordinate point, w.sub.1 represents a weight of the red value, G represents a green value of the coordinate point, w.sub.2 represents a weight of the green value, B represents a blue value of the coordinate point, and w.sub.3 represents a weight of the blue value). Please also see Fig. 1 and 4) and a three-dimensional image (Fig. 2. Paragraph [0053]-JIANG discloses in step 202, a three-dimensional image of an object is obtained. In step 206, luminance information and depth information are extracted from the three-dimensional image to generate a luminance image and a depth image, as shown in FIGS. 3b and 3c. Then, in step 210, depth values in the depth image are normalized to generate a normalized depth image (wherein normalization is performed by the following equation: ds = d- dmin / dmax – dmin where d represents a depth value of a coordinate point in the depth image, d.sub.min represents a minimum depth value in the depth image, d.sub.max represents a maximum depth value in the depth image, and ds represents a normalized depth value of the coordinate point in the depth image)). Please also see Fig. 1-2) by photographing a battery (Fig. 3a-d. Paragraph [0060]-JIANG discloses FIGS. 3a to 3d illustrate an embodiment of welding defect detection of a lithium battery sealing pin. However, it should be understood that the object in the image processing method of the present application may alternatively be a battery surface, a battery top cover weld, etc.);
a data processor (Fig. 4. Paragraph [0038]-JIANG discloses the instructions, when executed by a processor, cause the processor to perform the appearance detection method. Please also see Fig. 1-2) configured to generate fusion data based on the two-dimensional image and the three-dimensional image (Fig. 2. Paragraph [0055]-JIANG discloses in step 212, after steps 206 and 208 are completed, at least three same-location points with specificity may be selected from each of the grayscale image and the luminance image. These points with specificity are particular locations in patterns that are within the image and may be obtained by analysis of the patterns. In paragraph [0057]-JIANG discloses in step 214, a coordinate transformation matrix between the grayscale image and the luminance image is calculated based on coordinates of the three same-location points in each of the grayscale image and the luminance image. In paragraph [0058]-JIANG discloses in step 216, after the coordinate transformation matrix is calculated, the luminance image and the normalized depth image are aligned to the two-dimensional image based on the coordinate transformation matrix. In paragraph [0059]-JIANG discloses in step 218, the coordinate transformed luminance image and depth image are channel stacked with the grayscale image, to form a fused image having information of three channels. The color information, the luminance information, and the depth information may alternatively be fused by weighting to obtain an image having information of a single channel or multiple channels. Please also see Fig. 1 and 4, and read paragraph [0057 and 0061]);
a welding determiner configured to determine whether a weld joint of the battery is defective based on the welding area (Fig. 4. Paragraph [0055]-JIANG discloses FIGS. 3a to 3d illustrate an embodiment of welding defect detection of a lithium battery sealing pin. In the figures, two central points of angles between a straight weld and a circular weld, and the center point on the sealing pin may be selected as the three same-location points with specificity (wherein selection of the same-location points may be implemented using artificial intelligence algorithms). In paragraph [0061]-JIANG discloses in step 402, fused image data of a plurality of objects are obtained. In step 404, defect determining results of the plurality of objects are obtained. The defect determining results obtained in step 404 are determined by visual inspectors. Then, in step 406, the fused image data and the defect determining results of the plurality of objects are used to iteratively train a deep learning algorithm model, update the deep learning algorithm model. In step 408, after a useful deep learning algorithm model is obtained through training, a two-dimensional image and a three-dimensional image of a target object are acquired. In step 410, the two-dimensional image and the three-dimensional image of the target object are fused, to obtain fused image data of the target object. [0061]-JIANG discloses finally, in step 412, the fused image data of the target object is input into an updated deep learning algorithm model to obtain a defect determining result of the target object. Please also see Fig. 1-2).
JIANG fails to explicitly teach an object identifier configured to identify a welding area in the fusion data based on an artificial intelligence model trained to identify an object; and
However, PAN explicitly teaches an object identifier configured to identify a welding area in the fusion data (Paragraph [0105]-PAN discloses FIG. 9 is a flowchart of identifying welding defects in FIG. 1. Further in paragraph [0128]-PAN discloses wherein, the first floating-point data corresponds to pixels in the three-dimensional point cloud image, and includes coordinate information. The second floating-point data corresponds to pixels in the brightness map and includes brightness information. Therefore, coordinate information and brightness information can be obtained by combining the first floating point data and the second floating point data. Please also read paragraph [0107-0111]) based on an artificial intelligence model trained to identify an object (Paragraph [0085]-PAN discloses the three-dimensional point cloud image and brightness image of the object to be inspected are detected by using the defect recognition model, and the appearance characteristics and brightness characteristics of each weld bead in the object to be inspected are compared with each welding pattern stored in the defect recognition model. The shape features and brightness features matching the defects are compared one by one to identify whether there is a welding defect on the weld bead of the object to be detected, and if there is a welding defect, identify the location and type of the welding defect. By combining appearance features and brightness features to detect welding defects, the recognition rate of welding defects can be improved, thereby reducing the missed detection rate and overkill rate of welding defects. Please also read paragraph [0114-0115, 0121-0124 and 0130-0131]); and
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG of having a welding inspection apparatus comprising: a scanner configured to acquire a two-dimensional image and a three-dimensional image by photographing a battery; a data processor configured to generate fusion data based on the two-dimensional image and the three-dimensional image; and a welding determiner configured to determine whether a weld joint of the battery is defective based on the welding area, with the teachings of PAN of having an object identifier configured to identify a welding area in the fusion data based on an artificial intelligence model trained to identify an object.
Wherein JIANG’s apparatus having an object identifier configured to identify a welding area in the fusion data based on an artificial intelligence model trained to identify an object.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of defect detection, since both JIANG and PAN concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while PAN’s systems and methods improves the learning and recognition rate of welding defects, thereby reducing the missed detection rate and overkill rate of welding defects. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), Abstract and Paragraph [0115].
Regarding claim 2, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 1, although JIANG further teaches wherein the three-dimensional image comprises a plurality of pixels, a first height value being mapped to each of the plurality of pixels (Fig. 2. Paragraph [0053]-JIANG discloses in step 202, a three-dimensional image of an object is obtained. In step 206, luminance information and depth information are extracted from the three-dimensional image to generate a luminance image and a depth image. Then, in step 210, depth values in the depth image are normalized to generate a normalized depth image (wherein normalization is performed by the following equation: ds = d- dmin / dmax – dmin where d represents a depth value of a coordinate point in the depth image, d.sub.min represents a minimum depth value in the depth image, d.sub.max represents a maximum depth value in the depth image, and ds represents a normalized depth value of the coordinate point in the depth image), and the two-dimensional image (Fig. 9. Paragraph [0054]-JIANG discloses in step 204, a two-dimensional image of the object, as shown in FIG. 3a, is obtained. Then, in step 208, the two-dimensional color image with three (RGB) channels is grayed by weighting to obtain a single-channel grayscale image) comprises a plurality of pixels, a first luminance value being mapped to each of the plurality of pixels (Fig. 9. Paragraph [0054]-JIANG discloses in step 208, the two-dimensional color image with three (RGB) channels is grayed by weighting to obtain a single-channel grayscale image. Specifically, a grayscale value may be p=w.sub.1R+w.sub.2G+w.sub.3B where p represents a grayscale value of a coordinate point, R represents a red value of the coordinate point, w.sub.1 represents a weight of the red value, G represents a green value of the coordinate point, w.sub.2 represents a weight of the green value, B represents a blue value of the coordinate point, and w.sub.3 represents a weight of the blue value).
JIANG fails to explicitly teach a first height value within a first bit unit being mapped to each of the plurality of pixels, and a first luminance value within a second bit unit being mapped to each of the plurality of pixels.
However, PAN explicitly teaches a first height value within a first bit unit being mapped to each of the plurality of pixels, and a first luminance value within a second bit unit being mapped to each of the plurality of pixels (Paragraph [0105]-PAN discloses FIG. 9 is a flowchart of identifying welding defects in FIG. 1. In paragraph [0106]-PAN discloses S41, converting the three-dimensional point cloud image into floating point type image and normalizing to obtain the first floating point data, and normalizing the brightness image to obtain the second floating point data. In paragraph [0107]-PAN discloses the 3D point cloud image is converted into a floating-point image and then normalized, so that the gray value in the floating-point image is between 0 and 1, that is, the first floating-point number. The data is a value between 0 and 1, and a first floating-point data corresponds to a gray value of a pixel in the floating-point image wherein, the gray value in the floating-point image represents coordinate information (for example, height information). In paragraph [0111]-PAN discloses the brightness map is normalized so that the gray value in the brightness map is between 0 and 1, that is, the second floating-point data is a value between 0 and 1, and the two floating-point data correspond to the gray value of a pixel in the brightness map. Please also read paragraph [0112]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection apparatus, wherein the three-dimensional image comprises a plurality of pixels, a first height value being mapped to each of the plurality of pixels, and the two-dimensional image comprises a plurality of pixels, a first luminance value being mapped to each of the plurality of pixels, with the teachings of PAN of having a first height value within a first bit unit being mapped to each of the plurality of pixels, and a first luminance value within a second bit unit being mapped to each of the plurality of pixels.
Wherein JIANG’s apparatus having wherein the three-dimensional image comprises a plurality of pixels, a first height value within a first bit unit being mapped to each of the plurality of pixels, and the two-dimensional image comprises a plurality of pixels, a first luminance value within a second bit unit being mapped to each of the plurality of pixels.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of defect detection, since both JIANG and PAN concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while PAN’s systems and methods improves the learning and recognition rate of welding defects, thereby reducing the missed detection rate and overkill rate of welding defects. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), Abstract and Paragraph [0115].
Regarding claim 4, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 2, although JIANG further teaches wherein the data processor is configured to generate the fusion data (Fig. 7. Paragraph [0052]-JIANG discloses in step 112, after the coordinate transformation matrix is calculated, the two-dimensional image is aligned with the luminance image and the depth image based on the coordinate transformation matrix, to obtain fused image data. In paragraph [0059]-JIANG discloses the color information, the luminance information, and the depth information may be fused by weighting to obtain an image having information of a single channel or multiple channels) by using a second luminance value (Fig. 9. Paragraph [0054]-JIANG discloses in step 208, the two-dimensional color image with three (RGB) channels is grayed by weighting to obtain a single-channel grayscale image. Specifically, a grayscale value may be p=w.sub.1R+w.sub.2G+w.sub.3B where p represents a grayscale value of a coordinate point, R represents a red value of the coordinate point, w.sub.1 represents a weight of the red value, G represents a green value of the coordinate point, w.sub.2 represents a weight of the green value, B represents a blue value of the coordinate point, and w.sub.3 represents a weight of the blue value) and a second height value obtained by normalizing the first height value (Fig. 7. Paragraph [0053]-JIANG discloses in step 202, a three-dimensional image of an object is obtained. In step 206, luminance information and depth information are extracted from the three-dimensional image to generate a luminance image and a depth image. Then, in step 210, depth values in the depth image are normalized to generate a normalized depth image. Depth values in the depth image generated in step 206 may be very large, e.g., ten thousand or above, thus by means of normalization, the depth values may be limited between 0 and 1, which facilitates subsequent calculation and processing (wherein normalization is performed by the following equation: ds = d- dmin / dmax – dmin where d represents a depth value of a coordinate point in the depth image, d.sub.min represents a minimum depth value in the depth image, d.sub.max represents a maximum depth value in the depth image, and ds represents a normalized depth value of the coordinate point in the depth image (wherein depth represents “height” or Z-axis direction)).
JIANG fails to explicitly teach a second luminance value obtained by normalizing the first luminance value.
However, PAN explicitly teaches a second luminance value obtained by normalizing the first luminance value (Paragraph [0105]-PAN discloses FIG. 9 is a flowchart of identify welding defects in FIG. 1. In paragraph [0107]-PAN discloses the 3D point cloud image is converted into a floating-point image and then normalized, so that the gray value in the floating-point image is between 0 and 1, that is, the first floating-point number. Wherein, the gray value in the floating-point image represents coordinate information (for example, height information). In paragraph [0111]-PAN discloses the brightness map is normalized so that the gray value in the brightness map is between 0 and 1, that is, the second floating-point data is a value between 0 and 1, and the two floating-point data correspond to the gray value of a pixel in the brightness map. Wherein, the gray value in the brightness map represents brightness information (wherein the welding bead area in both images/maps may be selectively normalized). In paragraph [0110]-PAN discloses the floating-point image may be a 32-bit floating-point image or a 16-bit floating-point image).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection apparatus, wherein the data processor is configured to generate the fusion data by using a second luminance value and a second height value obtained by normalizing the first height value, with the teachings of PAN of having a second luminance value obtained by normalizing the first luminance value.
Wherein JIANG’s apparatus having wherein the data processor is configured to generate the fusion data by using a second luminance value obtained by normalizing the first luminance value and a second height value obtained by normalizing the first height value.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of defect detection, since both JIANG and PAN concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while PAN’s systems and methods improves the learning and recognition rate of welding defects, thereby reducing the missed detection rate and overkill rate of welding defects. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), Abstract and Paragraph [0115].
Regarding claim 5, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 4, JIANG further teaches wherein the data processor is configured to perform a weighted operation on the second luminance value and the second height value corresponding to each other to generate the fusion data (Fig. 7. Paragraph [0052]-JIANG discloses in step 112, after the coordinate transformation matrix is calculated, the two-dimensional image is aligned with the luminance image and the depth image based on the coordinate transformation matrix, to obtain fused image data. In paragraph [0059]-JIANG discloses the color information, the luminance information, and the depth information may be fused by weighting to obtain an image having information of a single channel or multiple channels. Please also read paragraph [0053-0055]).
Regarding claim 6, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 4, JIANG fails to explicitly teaches wherein each of the second luminance value and the second height value is a value within a third bit unit smaller than the first bit unit and the second bit unit.
However, PAN explicitly teaches wherein each of the second luminance value and the second height value is a value (Paragraph [0105]-PAN discloses FIG. 9 is a flowchart of identifying welding defects in FIG. 1. In paragraph [0106]-PAN discloses S41, converting the three-dimensional point cloud image into floating point type image and normalizing to obtain the first floating point data, and normalizing the brightness image to obtain the second floating point data. In paragraph [0107]-PAN discloses the 3D point cloud image is converted into a floating-point image and then normalized, so that the gray value in the floating-point image is between 0 and 1, that is, the first floating-point number. The data is a value between 0 and 1, and a first floating-point data corresponds to a gray value of a pixel in the floating-point image. Wherein, the gray value in the floating-point image represents coordinate information (for example, height information). In paragraph [0111]-PAN discloses the brightness map is normalized so that the gray value in the brightness map is between 0 and 1, that is, the second floating-point data is a value between 0 and 1, and the two floating-point data correspond to the gray value of a pixel in the brightness map. Wherein, the gray value in the brightness map represents brightness information (wherein the weld bead area in both images may be selected and normalized). Please also read paragraph [0112]) within a third bit unit smaller than the first bit unit and the second bit unit (Paragraph [0110]-PAN discloses the floating-point image may be, but not limited to, a 32-bit floating-point image or a 16-bit floating-point image. Therefore, it would have been obvious to a person of ordinary skill in the art for a third bit unit to be smaller than the first bit unit and the second bit unit. As discussed, PAN teaches the floating point data may be either 16 or 32-bits. Moreover, it is well-known that luminance and height values are encoded as bits, and the number of bits are a design choice to facilitate processing goals. Thus, it would have been obvious to use a third bit unit smaller than the first bit unit and the second bit unit because it reduces computational load, increases processing speed and improves the accuracy of normalization given the greater number of bits).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection apparatus, with the teachings of PAN of having wherein each of the second luminance value and the second height value is a value within a third bit unit smaller than the first bit unit and the second bit unit.
Wherein JIANG’s apparatus having wherein each of the second luminance value and the second height value is a value within a third bit unit smaller than the first bit unit and the second bit unit.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of defect detection, since both JIANG and PAN concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while PAN’s systems and methods improves the learning and recognition rate of welding defects, thereby reducing the missed detection rate and overkill rate of welding defects. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), Abstract and Paragraph [0115].
Regarding claim 7, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 4, JIANG further teaches wherein the second height value is proportional to a ratio of a first difference value between the first height value and a set lower limit value of the first height value, and a second difference value between a set upper limit value of the first height value and the set lower limit value (Fig. 2. Paragraph [0053]-JIANG discloses in step 206, luminance information and depth information are extracted from the three-dimensional image to generate a luminance image and a depth image. Then, in step 210, depth values in the depth image are normalized to generate a normalized depth image (wherein normalization is performed by the following equation: ds = d- dmin / dmax – dmin where d represents a depth value of a coordinate point in the depth image, d.sub.min represents a minimum depth value in the depth image, d.sub.max represents a maximum depth value in the depth image, and ds represents a normalized depth value of the coordinate point in the depth image).
Regarding claim 12, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 1, JIANG fails to explicitly teach wherein the welding area comprises a bead area, and the welding determiner is configured to determine whether the weld joint is defective according to whether the bead area exists in a preset region of interest.
However, PAN further teaches wherein the welding area comprises a bead area (Paragraph [0105]-PAN discloses FIG. 9 is a flowchart of identifying welding defects in FIG. 1. Further in paragraph [0085]-PAN discloses the three-dimensional point cloud image and brightness image of the object to be inspected are detected by using the defect recognition model, and the appearance characteristics and brightness characteristics of each weld bead in the object to be inspected are compared with each welding pattern stored in the defect recognition model), and the welding determiner is configured to determine whether the weld joint is defective according to whether the bead area exists in a preset region of interest (Paragraph [0091]-PAN discloses the welding defect is set in the preset area, so as to blur the defect of the welding bead on the top cover of the power battery when blurring the first image. The welding defect is set in the preset area, so as to blur the defect of the welding bead on the top cover of the power battery when blurring the first image. In paragraph [0105]-PAN discloses the shape features and brightness features matching the defects are compared one by one to identify whether there is a welding defect on the weld bead of the object to be detected, and if there is a welding defect, identify the location and type of the welding defect. Please also read paragraph [0109-0111, 0128-0129 and 0139]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection apparatus, with the teachings of PAN of having wherein the welding area comprises a bead area, and the welding determiner is configured to determine whether the weld joint is defective according to whether the bead area exists in a preset region of interest.
Wherein JIANG’s apparatus having wherein the welding area comprises a bead area, and the welding determiner is configured to determine whether the weld joint is defective according to whether the bead area exists in a preset region of interest.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of defect detection, since both JIANG and PAN concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while PAN’s systems and methods improves the learning and recognition rate of welding defects, thereby reducing the missed detection rate and overkill rate of welding defects. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), Abstract and Paragraph [0115].
Regarding claim 14, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 1, JIANG fails to explicitly teach wherein the welding area comprises a bead area, and the welding determiner is configured to determine whether the weld joint is defective according to a length of the bead area.
However, PAN explicitly teaches wherein the welding area comprises a bead area (Paragraph [0085]-PAN discloses the three-dimensional point cloud image and brightness image of the object to be inspected are detected by using the defect recognition model, and the appearance characteristics and brightness characteristics of each weld bead in the object to be inspected are compared with each welding pattern stored in the defect recognition model. The shape features and brightness features matching the defects are compared one by one to identify whether there is a welding defect on the weld bead of the object to be detected, and if there is a welding defect, identify the location and type of the welding defect. By combining appearance features and brightness features to detect welding defects, the recognition rate of welding defects can be improved, thereby reducing the missed detection rate and overkill rate of welding defects. Please also read paragraph [0091-0093 and 0107-0112]), and the welding determiner is configured to determine whether the weld joint is defective according to a length of the bead area (Paragraph [0128]-PAN discloses by semantically segmenting all the first floating-point data and all the second floating-point data, the feature points of each type of welding defect can be defined, and one feature point has a coordinate information and a brightness information. In paragraph [0129]-PAN discloses the blast points are dimples on the surface of the weld bead, which are larger than pinholes. Compared with the normal welding bead, the height of the solder in the polarized light is lower than that of the surrounding solder and presents a strip shape. Further in paragraph [0139]-PAN discloses the preset standard may be the external size, area, contour shape, distribution characteristics, etc. of each welding defect, which are specifically set according to actual work requirements and human experience. Please also read paragraph [0107]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection apparatus, with the teachings of PAN of having wherein the second height value is a value obtained by multiply the ratio by a maximum value within a third bit unit smaller than the first bit unit.
Wherein JIANG’s apparatus having wherein the second height value is a value obtained by multiplying the ratio by a maximum value within a third bit unit smaller than the first bit unit.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of defect detection, since both JIANG and PAN concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while PAN’s systems and methods improves the learning and recognition rate of welding defects, thereby reducing the missed detection rate and overkill rate of welding defects. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), Abstract and Paragraph [0115].
Regarding claim 15, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 14, JIANG further teaches wherein the welding determiner is configured to determine whether the weld joint is defective according to the first height value of the three-dimensional image (Fig. 2. Paragraph [0053]-JIANG discloses in step 202, a three-dimensional image of an object is obtained. In step 206, luminance information and depth information are extracted from the three-dimensional image to generate a luminance image and a depth image. Then, in step 210, depth values in the depth image are normalized to generate a normalized depth image (wherein normalization is performed by the following equation: ds = d- dmin / dmax – dmin where d represents a depth value of a coordinate point in the depth image, d.sub.min represents a minimum depth value in the depth image, d.sub.max represents a maximum depth value in the depth image, and ds represents a normalized depth value of the coordinate point in the depth image) corresponding to the bead area (Fig. 3a-d. Paragraph [0060]-JIANG discloses during battery production, detection procedures of scratches on the battery surface, defects of the battery top cover weld, and defects of the sealing pin weld are all important for ensuring safety of a battery after leaving the factory. FIGS. 3a to 3d illustrate an embodiment of welding defect detection of a lithium battery sealing pin. However, it should be understood that the object in the image processing method of the present application may alternatively be a battery surface, a battery top cover weld, etc.).
Regarding claim 16, JIANG explicitly teaches a welding inspection method (Fig. 4. Paragraph [0061]-JIANG discloses FIG. 4 illustrates a flowchart of an appearance detection method. In paragraph [0038]-JIANG discloses a fourth aspect of the present application provides a non-transitory storage medium storing instructions when executed by a processor, cause the processor to perform the appearance detection method. In paragraph [0060]-JIANG discloses FIGS. 3a to 3d illustrate an embodiment of welding defect detection of a lithium battery sealing pin. Please also see Fig. 1-3 and read paragraph [0050]) comprising:
photographing a battery (Fig. 3a-d. Paragraph [0060]-JIANG discloses FIGS. 3a to 3d illustrate an embodiment of welding defect detection of a lithium battery sealing pin. However, it should be understood that the object in the image processing method of the present application may alternatively be a battery surface, a battery top cover weld, etc.) to acquire a two-dimensional image (Fig. 2. Paragraph [0053]-JIANG discloses FIG. 2 illustrates a flowchart of an image processing method. In paragraph [0054]-JIANG discloses in step 204, a two-dimensional image of the object. Then, in step 208, the two-dimensional color image with three (RGB) channels is grayed by weighting to obtain a single-channel grayscale image (wherein a single channel grayscale image may be obtained using the following equation: p=w.sub.1R+w.sub.2G+w.sub.3B, where p represents a grayscale value of a coordinate point, R represents a red value of the coordinate point, w.sub.1 represents a weight of the red value, G represents a green value of the coordinate point, w.sub.2 represents a weight of the green value, B represents a blue value of the coordinate point, and w.sub.3 represents a weight of the blue value). Please also see Fig. 1 and 4) and a three-dimensional image (Fig. 2. Paragraph [0053]-JIANG discloses in step 202, a three-dimensional image of an object is obtained. In step 206, luminance information and depth information are extracted from the three-dimensional image to generate a luminance image and a depth image, as shown in FIGS. 3b and 3c. Then, in step 210, depth values in the depth image are normalized to generate a normalized depth image (wherein normalization is performed by the following equation: ds = d- dmin / dmax – dmin where d represents a depth value of a coordinate point in the depth image, d.sub.min represents a minimum depth value in the depth image, d.sub.max represents a maximum depth value in the depth image, and ds represents a normalized depth value of the coordinate point in the depth image)). Please also see Fig. 1-2);
generating fusion data based on the two-dimensional image and the three-dimensional image (Fig. 2. Paragraph [0055]-JIANG discloses in step 212, after steps 206 and 208 are completed, at least three same-location points with specificity may be selected from each of the grayscale image and the luminance image. These points with specificity are particular locations in patterns that are within the image and may be obtained by analysis of the patterns. In paragraph [0057]-JIANG discloses in step 214, a coordinate transformation matrix between the grayscale image and the luminance image is calculated based on coordinates of the three same-location points in each of the grayscale image and the luminance image. In paragraph [0058]-JIANG discloses in step 216, after the coordinate transformation matrix is calculated, the luminance image and the normalized depth image are aligned to the two-dimensional image based on the coordinate transformation matrix. In paragraph [0059]-JIANG discloses in step 218, the coordinate transformed luminance image and depth image are channel stacked with the grayscale image, to form a fused image having information of three channels. The color information, the luminance information, and the depth information may alternatively be fused by weighting to obtain an image having information of a single channel or multiple channels. Please also see Fig. 1 and 4, and read paragraph [0057 and 0061]);
determining whether a weld joint of the battery is defective based on the welding area (Fig. 4. Paragraph [0061]-JIANG discloses finally, in step 412, the fused image data of the target object is input into an updated deep learning algorithm model to obtain a defect determining result of the target object. Please also see Fig. 1-2, and read paragraph [0057]).
JIANG fails to explicitly teach identifying a welding area in the fusion data based on an artificial intelligence model trained to identify an object.
However, PAN explicitly teaches identifying a welding area in the fusion data (Paragraph [0128]-PAN discloses wherein, the first floating-point data corresponds to pixels in the three-dimensional point cloud image, and includes coordinate information. The second floating-point data corresponds to pixels in the brightness map and includes brightness information. Therefore, coordinate information and brightness information can be obtained by combining the first floating point data and the second floating point data) based on an artificial intelligence model trained to identify an object (Paragraph [0085]-PAN discloses the three-dimensional point cloud image and brightness image of the object to be inspected are detected by using the defect recognition model, and the appearance characteristics and brightness characteristics of each weld bead in the object to be inspected are compared with each welding pattern stored in the defect recognition model. The shape features and brightness features matching the defects are compared one by one to identify whether there is a welding defect on the weld bead of the object to be detected, and if there is a welding defect, identify the location and type of the welding defect. By combining appearance features and brightness features to detect welding defects, the recognition rate of welding defects can be improved, thereby reducing the missed detection rate and overkill rate of welding defects. Please also read paragraph [0114-0115, 0121-0124 and 0130-0131]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG of having a welding inspection method comprising: photographing a battery to acquire a two-dimensional image and a three-dimensional image; generating fusion data based on the two-dimensional image and the three- dimensional image; and determining whether a weld joint of the battery is defective based on the welding area, with the teachings of PAN of having identifying a welding area in the fusion data based on an artificial intelligence model trained to identify an object.
Wherein JIANG’s method having identifying a welding area in the fusion data based on an artificial intelligence model trained to identify an object.
The motivation behind the modification would have been to obtain a method that improves the efficiency, quality and efficacy of defect detection, since both JIANG and PAN concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while PAN’s systems and methods improves the learning and recognition rate of welding defects, thereby reducing the missed detection rate and overkill rate of welding defects. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), Abstract and Paragraph [0115].
Regarding claim 18, JIANG in view of PAN explicitly teaches the welding inspection method according to claim 16, although JIANG explicitly teaches wherein the generating of the fusion data comprises:
acquiring a second luminance value mapped to one pixel of a plurality of pixels of the two-dimensional image (Fig. 9. Paragraph [0054]-JIANG discloses in step 204, a two-dimensional image of the object, as shown in FIG. 3a, is obtained. Then, in step 208, the two-dimensional color image with three (RGB) channels is grayed by weighting to obtain a single-channel grayscale image. In step 208, the two-dimensional color image with three (RGB) channels is grayed by weighting to obtain a single-channel grayscale image. Specifically, a grayscale value may be p=w.sub.1R+w.sub.2G+w.sub.3B where p represents a grayscale value of a coordinate point, R represents a red value of the coordinate point, w.sub.1 represents a weight of the red value, G represents a green value of the coordinate point, w.sub.2 represents a weight of the green value, B represents a blue value of the coordinate point, and w.sub.3 represents a weight of the blue value), and acquiring a second height value by normalizing a first height value of a pixel corresponding to the one pixel of a plurality of pixels of the three-dimensional image (Fig. 2. Paragraph [0053]-JIANG discloses in step 202, a three-dimensional image of an object is obtained. In step 206, luminance information and depth information are extracted from the three-dimensional image to generate a luminance image and a depth image. Then, in step 210, depth values in the depth image are normalized to generate a normalized depth image (wherein normalization is performed by the following equation: ds = d- dmin / dmax – dmin where d represents a depth value of a coordinate point in the depth image, d.sub.min represents a minimum depth value in the depth image, d.sub.max represents a maximum depth value in the depth image, and ds represents a normalized depth value of the coordinate point in the depth image); and
generating the fusion data by using the second luminance value and the second height value (Fig. 2. Paragraph [0057]-JIANG discloses in step 214, a coordinate transformation matrix between the grayscale image and the luminance image is calculated based on coordinates of the three same-location points in each of the grayscale image and the luminance image. In paragraph [0058]-JIANG discloses in step 216, after the coordinate transformation matrix is calculated, the luminance image and the normalized depth image are aligned to the two-dimensional image based on the coordinate transformation matrix. In paragraph [0059]-JIANG discloses in step 218, the coordinate transformed luminance image and depth image are channel stacked with the grayscale image, to form a fused image having information of three channels. The color information, the luminance information, and the depth information may alternatively be fused by weighting to obtain an image having information of a single channel or multiple channels. Please also see Fig. 1 and 4, and read paragraph [0057 and 0061]).
JIANG fails to explicitly teach acquiring a second luminance value by normalizing a first luminance value mapped to one pixel of a plurality of pixels.
However, PAN explicitly teaches acquiring a second luminance value by normalizing a first luminance value mapped to one pixel of a plurality of pixels (Paragraph [0105]-PAN discloses FIG. 9 is a flowchart of identify welding defects in FIG. 1. In paragraph [0107]-PAN discloses the 3D point cloud image is converted into a floating-point image and then normalized, so that the gray value in the floating-point image is between 0 and 1, that is, the first floating-point number. Wherein, the gray value in the floating-point image represents coordinate information (for example, height information). In paragraph [0111]-PAN discloses the brightness map is normalized so that the gray value in the brightness map is between 0 and 1, that is, the second floating-point data is a value between 0 and 1, and the two floating-point data correspond to the gray value of a pixel in the brightness map. Wherein, the gray value in the brightness map represents brightness information (wherein the bead area in both images/maps may only be selected and normalized). Please also read paragraph [0112, 0115 and 0128]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection method, wherein the generating of the fusion data comprises: acquiring a second luminance value mapped to one pixel of a plurality of pixels of the two-dimensional image, and acquiring a second height value by normalizing a first height value of a pixel corresponding to the one pixel of a plurality of pixels of the three-dimensional image; and generating the fusion data by using the second luminance value and the second height value with the teachings of PAN of having acquiring a second luminance value by normalizing a first luminance value mapped to one pixel of a plurality of pixels.
Wherein JIANG’s method having wherein the generating of the fusion data comprises: acquiring a second luminance value by normalizing a first luminance value mapped to one pixel of a plurality of pixels of the two-dimensional image, and acquiring a second height value by normalizing a first height value of a pixel corresponding to the one pixel of a plurality of pixels of the three-dimensional image; and generating the fusion data by using the second luminance value and the second height value.
The motivation behind the modification would have been to obtain a method that improves the efficiency, quality and efficacy of defect detection, since both JIANG and PAN concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while PAN’s systems and methods improves the learning and recognition rate of welding defects, thereby reducing the missed detection rate and overkill rate of welding defects. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), Abstract and Paragraph [0115].
Regarding claim 19, JIANG in view of PAN explicitly teaches the welding inspection method according to claim 18, JIANG fails to explicitly teach wherein a maximum value of bits having the second height value is less than a maximum value of bits having the first height value, and a maximum value of bits having the second luminance value is less than a maximum value of bits having the first luminance value.
However, PAN explicitly teaches wherein a maximum value of bits having the second height value is less than a maximum value of bits having the first height value (Paragraph [0105]-PAN discloses FIG. 9 is a flowchart of identify welding defects in FIG. 1; FIG. 10 is a schematic diagram of a floating point type image in step S41; FIG. 11 is a schematic diagram of the luminance map in step S41. The step S40 specifically comprises steps S41 and S42. In paragraph [0106]-PAN discloses S41, converting the three-dimensional point cloud image into floating point type image and normalizing to obtain the first floating point data, and normalizing the brightness image to obtain the second floating point data. In paragraph [0107]-PAN discloses the 3D point cloud image is converted into a floating-point image and then normalized, so that the gray value in the floating-point image is between 0 and 1, that is, the first floating-point number. The data is a value between 0 and 1, and a first floating-point data corresponds to a gray value of a pixel in the floating-point image. Wherein, the gray value in the floating-point image represents coordinate information (for example, height information)), and a maximum value of bits having the second luminance value is less than a maximum value of bits having the first luminance value (Paragraph [0111]-PAN discloses the brightness map is normalized so that the gray value in the brightness map is between 0 and 1, that is, the second floating-point data is a value between 0 and 1, and the two floating-point data correspond to the gray value of a pixel in the brightness map. Wherein, the gray value in the brightness map represents brightness information (wherein the welding bead area in both images/maps may be selectively normalized)). Further in paragraph [0110]-PAN discloses the floating-point image may be, but not limited to, a 32-bit floating-point image or a 16-bit floating-point image. Therefore, it would have been obvious to a person of ordinary skill in the art to set the maximum value of bits having the second height value to be less than the maximum value of bits having the first height value. As discussed, PAN teaches setting the maximum value of bits to be higher or lower for both first and second brightness and coordinate (i.e. height) information. Moreover, it is well-known that luminance and height values are encoded as bits, and the number of bits are a design choice to facilitate processing goals. Thus, it would have been obvious for a maximum value of bits having the second height value to be less than a maximum value of bits having the first height value, and a maximum value of bits having the second luminance value to be less than a maximum value of bits having the first luminance value because this reduces computational load, increases processing speed and improves the accuracy of normalization given the greater number of bits used for the first values).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection method, with the teachings of PAN of having wherein a maximum value of bits having the second height value is less than a maximum value of bits having the first height value, and a maximum value of bits having the second luminance value is less than a maximum value of bits having the first luminance value.
Wherein JIANG’s method having wherein a maximum value of bits having the second height value is less than a maximum value of bits having the first height value, and a maximum value of bits having the second luminance value is less than a maximum value of bits having the first luminance value.
The motivation behind the modification would have been to obtain a method that improves the efficiency, quality and efficacy of defect detection, since both JIANG and PAN concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while PAN’s systems and methods improves the learning and recognition rate of welding defects, thereby reducing the missed detection rate and overkill rate of welding defects. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), Abstract and Paragraph [0115].
Regarding claim 20, JIANG in view of PAN explicitly teaches the welding inspection method according to claim 18, JIANG further teaches wherein the generating of the fusion data by using the second luminance value and the second height value comprises performing a weighted operation on the second luminance value and the second height value to acquire a result value and generating the fusion data including the result value (Fig. 2. Paragraph [0057]-JIANG discloses in step 214, a coordinate transformation matrix between the grayscale image and the luminance image is calculated based on coordinates of the three same-location points in each of the grayscale image and the luminance image. In paragraph [0058]-JIANG discloses in step 216, after the coordinate transformation matrix is calculated, the luminance image and the normalized depth image are aligned to the two-dimensional image based on the coordinate transformation matrix. In paragraph [0059]-JIANG discloses in step 218, the coordinate transformed luminance image and depth image are channel stacked with the grayscale image, to form a fused image having information of three channels. The color information, the luminance information, and the depth information may alternatively be fused by weighting to obtain an image having information of a single channel or multiple channels. Please also see Fig. 1 and 4, and read paragraph [0057 and 0061]).
Claims 3 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over JIANG et al. (US 20230281919 A1), hereinafter referenced as JIANG in view of PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), hereinafter referenced as PAN and in further view of STAUDENMAIER et al. (US 20160150164 A1), hereinafter referenced as STAUDENMAIER.
Regarding claim 3, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 2, although JIANG explicitly teaches wherein the data processor is configured to perform resizing to reduce the number of pixels of the three-dimensional image and generate the fusion data using the two-dimensional image and the resized three-dimensional image (Fig. 2. Paragraph [0020]-JIANG discloses the resolution of the three-dimensional image is low, so the luminance image and the depth image are aligned to the two-dimensional image. In paragraph [0059]-JIANG discloses in step 218, the coordinate transformed luminance image and depth image are channel stacked with the grayscale image, to form a fused image having information of three channels. Please also see Fig. 1 and 4, and read paragraph [0057 and 0061]).
JIANG in view of PAN fail to explicitly teach wherein the data processor is configured to perform resizing to reduce the number of pixels of the two-dimensional image and generate the fusion data using the resized two-dimensional image and the resized three-dimensional image.
However, STAUDENMAIER explicitly teaches perform resizing to reduce the number of pixels of the two-dimensional image and generate the fusion data using the resized two-dimensional image and the resized three-dimensional image (Fig. 7. Paragraph [0031]-STAUDENMAIER discloses the processing unit 40 or the GPU 42 may be arranged to merge the at least two input images to generate the view: e.g. a first input image Pic1 and a second input image Pic2 as schematically indicated in the FIGS. 1-3. The image-resizing unit 20 may resize the first input image Pic1 to a lower resolution version and output that lower resolution version to the memory 30. The memory 30 may store the lower resolution version of the first input image Pic1 and a maximum resolution version of the second input image Pic2. In paragraph [0041]-STAUDENMAIER discloses the multi-camera view system 100, 110 or 120 may be able to generate a two dimensional, or a three-dimensional output image. Please also read paragraph [0016]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection apparatus, wherein the data processor is configured to perform resizing to reduce the number of pixels of the three-dimensional image and generate the fusion data using the two-dimensional image and the resized three-dimensional image, with the teachings of STAUDENMAIER of having wherein the data processor is configured to perform resizing to reduce the number of pixels of the two-dimensional image and generate the fusion data using the resized two-dimensional image and the resized three-dimensional image.
Wherein JIANG’s apparatus having wherein the data processor is configured to perform resizing to reduce the number of pixels of the two-dimensional image and the three-dimensional image and generate the fusion data using the resized two-dimensional image and the resized three-dimensional image.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of defect detection, since both JIANG and STAUDENMAIER concern image analysis and image fusion. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while STAUDENMAIER’s systems and methods improves bandwidth and computing power required for image processing. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and STAUDENMAIER et al. (US 20160150164 A1), Abstract and Paragraph [0002-0003].
Regarding claim 17, JIANG in view of PAN explicitly teaches the welding inspection method according to claim 16, although JIANG explicitly teaches wherein the generating of the fusion data comprises:
performing resizing to reduce the number of pixels of the three-dimensional image (Fig. 2. Paragraph [0020]-JIANG discloses the resolution of the three-dimensional image is low, so the luminance image and the depth image are aligned to the two-dimensional image);
generating the fusion data using the two-dimensional image and the resized three-dimensional image (Fig. 2. Paragraph [0059]-JIANG discloses in step 218, the coordinate transformed luminance image and depth image are channel stacked with the grayscale image, to form a fused image having information of three channels. Please also see Fig. 1 and 4, and read paragraph [0057 and 0061]).
JIANG in view of PAN fails to explicitly teach performing resizing to reduce the number of pixels of the two-dimensional image; and generating the fusion data using the resized two-dimensional image and the resized three-dimensional image.
However, STAUDENMAIER explicitly teaches performing resizing to reduce the number of pixels of the two-dimensional image (Fig. 1. Paragraph [0031]-STAUDENMAIER discloses the image-resizing unit 20 may resize the first input image Pic1 to a lower resolution version and output that lower resolution version to the memory 30. The memory 30 may store the lower resolution version of the first input image Pic1 and a maximum resolution version of the second input image Pic2. In paragraph [0041]-STAUDENMAIER discloses the multi-camera view system 100, 110 or 120 may be able to generate a two dimensional, or a three-dimensional output image. Please also read paragraph [0016]); and
generating the fusion data using the resized two-dimensional image and the resized three-dimensional image (Fig. 1. Paragraph [0031]-STAUDENMAIER discloses the processing unit 40 or the GPU 42 may be arranged to merge the at least two input images to generate the view: e.g. a first input image Pic1 and a second input image Pic2 as schematically indicated in the FIGS. 1-3. Please also read paragraph [0016]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection method, wherein the generating of the fusion data comprises: performing resizing to reduce the number of pixels of the three-dimensional image; and generating the fusion data using the two-dimensional image and the resized three-dimensional image, with the teachings of STAUDENMAIER of having performing resizing to reduce the number of pixels of the two-dimensional image; and generating the fusion data using the resized two-dimensional image and the resized three-dimensional image.
Wherein JIANG’s method having wherein the generating of the fusion data comprises: performing resizing to reduce the number of pixels of the two-dimensional image and the three-dimensional image; and generating the fusion data using the resized two-dimensional image and the resized three-dimensional image.
The motivation behind the modification would have been to obtain a method that improves the efficiency, quality and efficacy of defect detection, since both JIANG and STAUDENMAIER concern image analysis and image fusion. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while STAUDENMAIER’s systems and methods improves bandwidth and computing power required for image processing. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and STAUDENMAIER et al. (US 20160150164 A1), Abstract and Paragraph [0002-0003].
Claim 8-9 are rejected under 35 U.S.C. 103 as being unpatentable over JIANG et al. (US 20230281919 A1), hereinafter referenced as JIANG in view of PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), hereinafter referenced as PAN in further view of YUAN et al. (YUAN YING et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), hereinafter referenced as YUAN.
Regarding claim 8, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 7, JIANG fails to explicitly teach wherein the second height value is a value obtained by multiplying the ratio by a maximum value.
However, YUAN explicitly teaches wherein the second height value (Paragraph [019-0018]-YUAN discloses the height value of the pixel points in the normalized image is in the range of 0-255) is a value obtained by multiplying the ratio by a maximum value (Paragraph [098]-YUAN discloses the 3D camera firstly acquires the height value of the measured target, and then converts the acquired height value into the depth image. Further in paragraph [0111]-YUAN discloses S203, calculating the difference value between the height target threshold value and the first median value to obtain a first difference value diff1. In paragraph [0112]-YUAN discloses the first difference value may describe a difference between an average level of the height values of a row of pixel points in the detection area and a height target threshold. In paragraph [0115]-YUAN discloses s204, adding the first difference value to the height values of the pixel points of the row. In paragraph [0128-0131]-YUAN discloses the step of normalizing the corrected image to obtain a normalized image includes: respectively calculating median values of the height values of the pixel points of each row in the corrected image to obtain a second median value Med2 corresponding to each row. And multiply the height value HValNew of each row of pixel points in the corrected image by a first coefficient, and subtracting the corresponding second median value Med2 to multiply by a second coefficient to obtain a first height value. In paragraph [0132]-YUAN discloses a first coefficient and a second coefficient are set, wherein the first coefficient and the second coefficient are smaller than 1. In paragraph [0134]-YUAN discloses a height value HValNew of a pixel point may be multiplied by a first coefficient, and after subtracting the second median value Med2 from the first coefficient. Please also read paragraph [0]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection apparatus, with the teachings of YUAN of having wherein the second height value is a value obtained by multiplying the ratio by a maximum value.
Wherein JIANG’s apparatus having wherein the second height value is a value obtained by multiplying the ratio by a maximum value.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of defect detection, since both JIANG and YUAN concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while YUAN’s systems and methods improves the accuracy of defect height value. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and YUAN et al. (YUAN YING et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), Abstract and Paragraph [01].
Although YUAN explicitly teaches wherein the second height value is a value obtained by multiplying the ratio by a maximum value.
JIANG and in view of YUAN fails to explicitly teach wherein the second height value is a value within a third bit unit smaller than the first bit unit.
However, PAN explicitly teaches wherein the height value (Paragraph [0105]-PAN discloses FIG. 9 is a flowchart of identify welding defects in FIG. 1; FIG. 10 is a schematic diagram of a floating point type image in step S41; FIG. 11 is a schematic diagram of the luminance map in step S41. The step S40 specifically comprises steps S41 and S42. In paragraph [0106]-PAN discloses S41, converting the three-dimensional point cloud image into floating point type image and normalizing to obtain the first floating point data, and normalizing the brightness image to obtain the second floating point data. In paragraph [0107]-PAN discloses the 3D point cloud image is converted into a floating-point image and then normalized, so that the gray value in the floating-point image is between 0 and 1, that is, the first floating-point number. The data is a value between 0 and 1, and a first floating-point data corresponds to a gray value of a pixel in the floating-point image. Wherein, the gray value in the floating-point image represents coordinate information (for example, height information). In paragraph [0111]-PAN discloses the brightness map is normalized so that the gray value in the brightness map is between 0 and 1, that is, the second floating-point data is a value between 0 and 1, and the two floating-point data correspond to the gray value of a pixel in the brightness map. Wherein, the gray value in the brightness map represents brightness information (wherein the welding bead area in both images/maps may be selectively normalized). In paragraph [0112]-PAN discloses the weld bead area in the brightness map can be normalized) is a value within a third bit unit smaller than the first bit unit (Paragraph [0110]-PAN discloses the floating-point image may be, but not limited to, a 32-bit floating-point image or a 16-bit floating-point image. Therefore, it would have been obvious to a person of ordinary skill in the art for a third bit unit to be smaller than the first bit unit and the second bit unit. As discussed, PAN teaches the floating point data may be either 16 or 32-bits. Moreover, it is well-known that luminance and height values are encoded as bits, and the number of bits are a design choice to facilitate processing goals. Thus, it would have been obvious to use a third bit unit smaller than the first bit unit and the second bit unit because it reduces computational load, increases processing speed and improves the quality of normalization given the greater number of initial bits used).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN and in further view of YUAN of having a welding inspection apparatus, with the teachings of PAN of having wherein the second height value is a value within a third bit unit smaller than the first bit unit.
Wherein JIANG’s apparatus having wherein the second height value is a value obtained by multiplying the ratio by a maximum value within a third bit unit smaller than the first bit unit.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of defect detection, since both JIANG and PAN concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while PAN’s systems and methods improves the learning and recognition rate of welding defects, thereby reducing the missed detection rate and overkill rate of welding defects. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), Abstract and Paragraph [0115].
Regarding claim 9, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 7, although JIANG explicitly teaches wherein the set upper limit value is a value obtained by a first set value of the first height value of each of the plurality of pixels included in the three-dimensional image, and the set lower limit value is a value obtained by subtracting a second set value (Fig. 2. Paragraph [0053]-JIANG discloses in step 202, a three-dimensional image of an object is obtained. In step 206, luminance information and depth information are extracted from the three-dimensional image to generate a luminance image and a depth image. Then, in step 210, depth values in the depth image are normalized to generate a normalized depth image (wherein normalization is performed by the following equation: ds = d- dmin / dmax – dmin where d represents a depth value of a coordinate point in the depth image, d.sub.min represents a minimum depth value in the depth image, d.sub.max represents a maximum depth value in the depth image, and ds represents a normalized depth value of the coordinate point in the depth image).
JIANG in view of PAN fails to explicitly teach a value obtained by adding a first set value to a middle value of the first height value of each of the plurality of pixels included in the three-dimensional image, and a value obtained by subtracting a second set value from the middle value.
However, YUAN explicitly teaches a value obtained by adding a first set value to a value of the first height value of each of the plurality of pixels, and a value obtained by subtracting a second set value from the middle value (Paragraph [0199]-YUAN discloses a preset unit for presetting a height target threshold. In paragraph [0200]-YUAN discloses the first median value calculation unit is used for calculating a median value of the height values of the pixel points of one row in the detection area to obtain a first median value. In paragraph [0201]-YUAN discloses a first difference calculating unit, configured to calculate a difference between the height target threshold and the first median value, to obtain a first difference. In paragraph [0202]-YUAN discloses the adding unit is used for adding the first difference value to the height values of the pixel points of the row. In paragraph [0208]-YUAN discloses the first height value calculation unit is used for multiplying the height value of each row of pixel points in the corrected image by a first coefficient, and subtracting the corresponding second median value to multiply the second coefficient to obtain a first height value. In paragraph [0209]-YUAN discloses a normalized image determining unit for adding a preset height value to the first height value to obtain a normalized image. Please also read paragraph [0151-0156]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection apparatus, wherein the set upper limit value is a value obtained by a first set value of the first height value of each of the plurality of pixels included in the three-dimensional image, and the set lower limit value is a value obtained by subtracting a second set value, with the teachings of YUAN of having a value obtained by adding a first set value to a value of the first height value of each of the plurality of pixels, and a value obtained by subtracting a second set value from the middle value.
Wherein JIANG’s apparatus having wherein the set upper limit value is a value obtained by adding a first set value to a middle value of the first height value of each of the plurality of pixels included in the three-dimensional image, and the set lower limit value is a value obtained by subtracting a second set value from the middle value.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of defect detection, since both JIANG and YUAN concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while YUAN’s systems and methods improves the accuracy of defect height value. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and YUAN et al. (YUAN YING et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), Abstract and Paragraph [01].
Claim 10-11 are rejected under 35 U.S.C. 103 as being unpatentable over JIANG et al. (US 20230281919 A1), hereinafter referenced as JIANG in view of PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), hereinafter referenced as PAN and in further view of DING et al. (DING YUE et al., machine translation of Chinese Patent Publication CN119831908A, " Image processing method and related equipment"), hereinafter referenced as DING.
Regarding claim 10, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 4, JIANG in view of PAN fails to explicitly teach wherein the second luminance value is proportional to a ratio of the first luminance value, and a value obtained by adding 1 to a maximum value of the second bit unit.
However, DING explicitly teaches wherein the second luminance value is proportional to a ratio of the first luminance value, and a value obtained by adding 1 to a maximum value of the second bit unit (Paragraph [0111]-DING discloses the second adjustment coefficient may be equal to 1, and the third adjustment coefficient may be equal to 1. In paragraph [0116]-DING discloses the first brightness adjustment coefficient may be the ratio of the current display brightness to the maximum display brightness. In paragraph [0118]-DING discloses brightness information of each pixel in the second area can be digitized (for example, normalized) to obtain a brightness value, and then the second brightness adjustment coefficient of the pixel is calculated based on the brightness value. If the second area includes N pixels, the second brightness adjustment coefficient of the i-th pixel satisfies the calculation formula: Q2i=1+Li/Lmax. Taking the brightness information as an 8-bit value, the brightness information can be digitized as 0 to 255. If the brightness value of a pixel is C, the second adjustment coefficient Q2 corresponding to the pixel is Q2=1+C/255. The second brightness adjustment coefficient of each pixel in the second area is the sum of 1 and the normalized brightness value of the pixel. In paragraph [0120]-DING discloses the second brightness adjustment coefficient may also be 1 (wherein the depth information and normalized depth information may have a bit width of 8 bits, and the brightness information may have a bit width of 8, 10 or higher). Please also read paragraph [0141-0142]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection apparatus, with the teachings of DING of having wherein the second luminance value is proportional to a ratio of the first luminance value, and a value obtained by adding 1 to a maximum value of the second bit unit.
Wherein JIANG’s apparatus having wherein the second luminance value is proportional to a ratio of the first luminance value, and a value obtained by adding 1 to a maximum value of the second bit unit.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of welding bead defect detection, since both JIANG and DING concern image analysis using height and luminance. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while DING’s systems and methods improves image fusion, display and system efficiency. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and SHU et al. (US 20230281785 A1), Abstract and Paragraph [0015, 0058, 0077 and 0160].
Regarding claim 11, JIANG in view of PAN and in further view of DING explicitly teaches the welding inspection apparatus according to claim 10, JIANG in view of PAN fail to explicitly teach wherein the second luminance value is a value obtained by multiplying the ratio by a maximum value within a third bit unit smaller than the second bit unit.
However, DING explicitly teaches wherein the second luminance value is a value (Paragraph [0118]-YUAN discloses the brightness information of each pixel in the second area can be digitized (for example, normalized) to obtain a brightness value, and then the second brightness adjustment coefficient of the pixel is calculated based on the brightness value) obtained by multiplying the ratio by a maximum value within a third bit unit smaller than the second bit unit (Paragraph [0116]-DING discloses when the target display brightness is determined by comparing the brightness threshold and the maximum display brightness, if the brightness threshold is less than the maximum display brightness, the brightness threshold is determined as the target display brightness, and the first brightness adjustment coefficient is the ratio of the current display brightness to the brightness threshold, that is, the reciprocal of the preset multiple; if the brightness threshold is greater than or equal to the maximum display brightness, the maximum display brightness is determined as the target display brightness, and the first brightness adjustment coefficient may be the ratio of the current display brightness to the maximum display brightness. When the maximum display brightness is fixed as the target display brightness, the first brightness adjustment coefficient may be the ratio of the current display brightness to the maximum display brightness. The first brightness adjustment coefficient is the ratio of the current display brightness to the target display brightness (wherein the encoded brightness information may have a bit width of 8, 10 or higher, and the encoded depth information and normalized depth information may have a bit width of 8 bits). Please also read paragraph [0108-0117, and 0141-0142]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection apparatus, with the teachings of DING of having wherein the second luminance value is a value obtained by multiplying the ratio by a maximum value within a third bit unit smaller than the second bit unit.
Wherein JIANG’s apparatus having wherein the second luminance value is a value obtained by multiplying the ratio by a maximum value within a third bit unit smaller than the second bit unit.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of welding bead defect detection, since both JIANG and DING concern image analysis using height and luminance. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while DING’s systems and methods improves image fusion, display and system efficiency. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and SHU et al. (US 20230281785 A1), Abstract and Paragraph [0015, 0058, 0077 and 0160].
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over JIANG et al. (US 20230281919 A1), hereinafter referenced as JIANG in view of PAN et al. (PAN YONG et al., Machine Translation of Chinese Patent Publication CN116051542A, "Defect detection method and defect detection device"), hereinafter referenced as PAN and in further view of HUANG et al. (US 20240221147 A1), hereinafter referenced as HUANG.
Regarding claim 13, JIANG in view of PAN explicitly teaches the welding inspection apparatus according to claim 12, JIANG in view of PAN fail to explicitly teach wherein the welding area further comprises an emboss area, and the region of interest is the emboss area.
However, HUANG explicitly teaches wherein the welding area further comprises an emboss area (Fig. 4. Paragraph [0080]-HUANG discloses the bulge 212 of the connecting piece 21 may be formed by stamping, so as to improve space utilization of a battery. In paragraph [0094]-HUANG discloses the bottom portion 2122 protruding from the surface of the piece body 211 and the side wall 2123 connecting the bottom portion 2122 and the mouth portion 2121 are formed by using a stamping device to stamp at a position corresponding to the mouth portion, and the center A 2 of the inspection contour is the center of the bottom portion 2122 formed by stamping. Please also see Fig. 1), and the region of interest is the emboss area (Fig. 4. Paragraph [0082]-HUANG discloses FIG. 4 is a flowchart of a connecting piece quality inspection method 400. In paragraph [0083]-HUANG discloses Step S 401 . Obtain an inspection image of a connecting piece, where the inspection image covers a bulge. In paragraph [0084]-HUANG discloses the inspection image may be obtained by an image obtaining apparatus, and the inspection image can show complete image characteristics of the bulge of the connecting piece. In paragraph [0085]-HUANG discloses step S 402 determine, in the inspection image, position information of a reference contour of the bulge and position information of an inspection contour of the bulge. In paragraph [0087]-HUANG discloses step S 403 determine a quality inspection result of the connecting piece based on the position information of the reference contour and the position information of the inspection contour).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of JIANG in view of PAN of having a welding inspection apparatus, with the teachings of HUANG of having wherein the welding area further comprises an emboss area, and the region of interest is the emboss area.
Wherein JIANG’s apparatus having wherein the welding area further comprises an emboss area, and the region of interest is the emboss area.
The motivation behind the modification would have been to obtain an apparatus that improves the efficiency, quality and efficacy of welding bead defect detection, since both JIANG and HUANG concern image analysis and defect detection. Wherein JIANG’s systems and methods improve the accuracy of detection and reduces missed and false detection (false positive), while HUANG’s systems and methods improve efficiency of connecting piece quality inspection. Please see JIANG et al. (US 20230281919 A1), Paragraph [0062] and HUANG et al. (US20240221147A1), Abstract and Paragraph [0005 and 0010].
Conclusion
Listed below are the prior arts made of record and not relied upon but are considered pertinent to applicant`s disclosure.
SHU et al. (US 20230281785 A1)- The present application provides a method and system for defect detection. The method includes: acquiring a two-dimensional (2D) picture of an object to be detected; inputting the acquired 2D picture to a trained defect segmentation model to obtain a segmented 2D defect mask, where the defect segmentation model is trained based on a multi-level feature extraction instance segmentation network with intersection over union (IoU) thresholds being increased level by level, and the 2D defect mask includes information about a defect type, a defect size, and a defect location of a segmented defect region; and determining the segmented 2D defect mask based on a predefined defect rule to output a defect detection result...…....................... Please see Fig. 1-8. Abstract.
JIANG et al. (US 20230245457 A1)- An image recognition method may include: acquiring a target image, where the target image may include a weld bead region; performing initial segmentation on the target image, to obtain a first recognition result, where the first recognition result may include first recognition information for the weld bead region in the target image; performing feature extraction on the target image, to obtain a region representation; obtaining a context representation based on the first recognition result and the region representation, where the context representation may be used for representing a correlation between each pixel and remaining pixels in the target image; and obtaining a second recognition result based on the context representation, where the second recognition result may include second recognition information for the weld bead region in the target image..…....................... Please see Fig. 1-7. Abstract.
PESME et al. (US 20160193680 A1)- An automated welding device comprises a camera, processing circuitry, a welding torch, and an electromechanical subsystem. The camera is operable to capture, using visible and/or infrared wavelengths, a high dynamic range image of one or more workpieces. The processing circuitry is operable to process the image for determination of physical characteristics of the one or more workpieces. The processing circuitry may be operable to generate, during welding of the one or more workpieces by the welding torch, electrical signals which are based on the determined physical characteristics of the one or more workpieces, and which control one or more welding parameters of the automated welding device during the welding of the one or more workpieces. The electromechanical subsystem is operable to convert the electrical signals into the one or more welding parameters of the automated welding device.…....................... Please see Fig. 2 and 6-7. Abstract.
BOHM et al. (US 20210181150 A1)- A method for characterizing at least one joined connection between at least two components, whereby an eddy-current sensor is consecutively moved several times over the at least one weld, thereby generating a plurality of data sets of the detected measuring signals in various parallel sectional planes of the weld, and whereby, on the basis of the plurality of data sets, a projection data set is subsequently determined as the measure of the spatial distribution of the measuring signals along the at least one joined connection..…....................... Please see Fig. 1-5. Abstract.
Rajagopalan et al. (US 20200033063 A1)- The present application relates to a field system and methods that can be deployed in the application of pipe welding. The field system provides many embodiments relating to pipe welding systems and methods, that can be used in combination with one another, or individually. Such welding systems and methods, include, for example, internal welding systems and methods, tie-in welding system and methods, pipe inspection systems and methods, pipe handling systems and methods, internal pipe cooling systems and methods, non-destructive testing systems and methods, as well as remote interface and database systems and methods (uLog), to name a few. The application further relates to welded pipes that result from some or all of such processes...…....................... Please see para. [0305-0307 and 1156-1157]. Abstract.
GURUMURTHY et al. (US 20230125477 A1)- Apparatuses, systems, and techniques to facilitate feature detection of a manufactured object such as a PCB using combined images of said manufactured object. In at least one embodiment, an automated optical inspection system (AOI) comprising one or more neural networks can infer based, at least in part, on combined images of a PCB the existence of defects on said PCB...…....................... Please see Paragraph [0066, 0087, 0159, 0162, 0325, 0493, 0513]. Abstract.
HSU et al. (US 20160267806 A1)- Methods and apparatus to provide visual information associated with welding operations are disclosed. An weld training system includes a display, a camera, a communications device, and a welding helmet. The communications device communicates with welding equipment. The welding helmet has a view port. The communications device is configured to hold the camera, the communications device, and the display such that, when the welding helmet is worn by a wearer, the display is viewable by the wearer, the camera has a view through the view port such that the display displays to the wearer images taken by the camera through the view port and displays a simulated object generated based on information received from the welding equipment via the communications device..…....................... Please see Fig. 6-10. Abstract.
Any inquiry concerning this communication or earlier communications from the examiner
should be directed to Aaron Bonansinga whose telephone number is (703) 756-5380 The examiner can normally be reached on Monday-Friday, 9:00 a.m. - 6:00 p.m. ET.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s
supervisor, Chineyere Wills-Burns can be reached by phone at (571) 272-9752. The fax phone number for the organization where this application or proceeding is assigned is (571) 273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/AARON TIMOTHY BONANSINGA/Examiner, Art Unit 2673
/CHINEYERE WILLS-BURNS/Supervisory Patent Examiner, Art Unit 2673
Prosecution Insights