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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 15 September, 2026 has been entered.
Response to Amendment
The amendment filed 15 September, 2026 has been entered.
The amendment of claims 1, 21, and 28 has been acknowledged.
Response to Arguments
Applicant’s arguments, see page 12, section “35 U.S.C. § 102”, filed 15 September, 2026 with respect to the rejection of claims 1 – 4, 21 – 24, and 28 - 31 under 35 U.S.C. § 102 have been fully considered and are persuasive. The rejection of claims 1 – 4, 21 – 24, and 28 - 31 under 35 U.S.C. § 102 has been withdrawn.
Applicant’s arguments, see page 15, section “35 U.S.C. § 103”, filed 15 September, 2026 with respect to the rejection of claims 5, - 7, 25 – 27, 32 and 33 under 35 U.S.C. § 103 have been fully considered and are persuasive. The rejection of claims , 5 - 7, 25 – 27, 32 and 33 under 35 U.S.C. § 103 have been withdrawn. However, upon further examination, a new rejection has been made under 35 U.S.C. § 103.
Claim Rejections - 35 USC § 103
Claims 1 – 5, 7, 21 – 25, 27 – 31, and 33 are rejected under 35 U.S.C. 103 as being unpatentable over Takasu et al (U.S. Patent Publication No. 2022/0189035 A1, hereinafter “Takasu”) in view of Soderberg et al (U.S. Patent Publication No. 2011/0007967 A1, hereinafter “Soderberg) and further in view of Peterson et al (U.S. Patent No. 10,930,033, hereinafter “Peterson”).
Regarding claim 1, Takasu teaches a method comprising:
generating, for a first target pixel (Figures 8A, Ref. No. LB(1) and 10A – 10C; ¶ 0078: According to the embodiment described above, the CPU 310 may set a plurality of larger blocks LB in the subject image, e.g., the medium image Is, and a plurality of smaller blocks SB smaller than the larger blocks LB (S415 in FIG. 7, S425 in FIG. 8); ¶ 0087: FIGS. 10A-10C are illustrative views of histograms. FIG. 10A shows a histogram of the larger block LB shown in FIG. 8B. FIG. 10B shows a histogram of the smaller block SBa shown in FIG. 8B. FIG. 10C shows a histogram of the smaller block SBb shown in FIG. 8B. The histograms shown in FIGS. 10A-10B are graphs with the horizontal axis indicating the brightness value and the vertical axis indicating a number of pixels included in each class of the brightness values.; Examiner’s note: The amendment to the independent claim states “a pixel rank histogram comprising ranking bins corresponding to different ranges of different pluralities of pixel values”, however these pixel ranges and pixel values are not defined. When reviewing the applicant’s specification filed 16 July, 2024, ¶ 0052 states “For instance, the edge detection system 102 generates a pixel rank histogram with a first bin for a first range of values (e.g., 0-50), a second bin with a second range of values (e.g., 51-100), a third bin for a third range of values, (e.g., 101-150) and so on for a number of ranking bins and/or for a range of pixel values (e.g., 0-255) (emphasis added)”. Under broadest reasonable interpretation, in view of the applicant’s specification, the different ranges of different pluralities of pixel values as claimed are understood to be read on by the histograms of Takasu’s Figure 10A – 10C, as Takasu comprises a plurality of these “bins” and ranges of pixels. To overcome Takasu for this limitation, the applicant may amend this limitation further to identify the specific bin ranges as disclosed in ¶ 0052 of their specification.);
assigning a first pixel rank to the first target pixel based on a position of a ranking bin within the pixel rank histogram into which a pixel value of the first pixel falls (¶ 0062: In S420, the CPU 310 obtains a median value M among the brightness values of the K pixels in the marked larger block LB as a feature value of the marked larger block. For example, when K is an even number, and when the brightness values in the K pixels are arranged in an increasing order, the median value M is an average of the (K/2)th brightness value and the {(K/2)+1}th brightness value.; Examiner’s note: The examiner is interpreting the “first pixel rank” to be the median value M determined using each pixel value from within the block. This M value would be generated based on the value of “the target pixel” as well as all other pixels within the block and is based on the ranking bins (Per Fig. 10A – 10C, 0 – 255 individually represent pixel bins of ranges 0, 1, 2, …, 255.) which identify the pixel value for each pixel.);
generating, for a second target pixel, a second local histogram ranking of pixels within a second neighborhood defined by moving the sliding pixel window within the raster image (Figures 8A, Ref. No. LB(2) and 10A – 10C; ¶ 0078: According to the embodiment described above, the CPU 310 may set a plurality of larger blocks LB in the subject image, e.g., the medium image Is, and a plurality of smaller blocks SB smaller than the larger blocks LB (S415 in FIG. 7, S425 in FIG. 8); ¶ 0087: FIGS. 10A-10C are illustrative views of histograms. FIG. 10A shows a histogram of the larger block LB shown in FIG. 8B. FIG. 10B shows a histogram of the smaller block SBa shown in FIG. 8B. FIG. 10C shows a histogram of the smaller block SBb shown in FIG. 8B. The histograms shown in FIGS. 10A-10B are graphs with the horizontal axis indicating the brightness value and the vertical axis indicating a number of pixels included in each class of the brightness values.);
assigning a second pixel rank to the second target pixel based on a position of a ranking bin within the pixel rank histogram into which a pixel value of the second target pixel falls (¶ 0062: In S420, the CPU 310 obtains a median value M among the brightness values of the K pixels in the marked larger block LB as a feature value of the marked larger block. For example, when K is an even number, and when the brightness values in the K pixels are arranged in an increasing order, the median value M is an average of the (K/2)th brightness value and the {(K/2)+1}th brightness value.; Examiner’s note: The examiner is interpreting the “second pixel rank” to be the median value M determined using each pixel value from within the block. This M value would be generated based on the value of “the target pixel” as well as all other pixels within the block and is based on the ranking bins (Per Fig. 10A – 10C, 0 – 255 individually represent pixel bins of ranges 0, 1, 2, …, 255.) which identify the pixel value for each pixel.);
providing the edge for display based on determining the edge strength for the region of the raster image (¶ 0095: Moreover, according to the embodiment described above, the CPU 310 generates local edge image data in S320 (see FIG. 5), which indicates the pixels determined to form edges through the edge-detection process in S300 (see FIG. 5) as local edge pixels. Thus, the edge image data, in which the edges of a local object in the image are accurately specified, may be generated.).
Takasu does not explicitly teach a raster image; and determining, for a region of the raster image comprising the first target pixel and the second target pixel, an edge strength for an edge depicted in the raster image by comparing pixel ranks assigned to pixels in the region including the first pixel rank and the second pixel rank.
However, Soderberg teaches determining, for a region of the raster image comprising the first target pixel and the second target pixel, an edge strength for an edge depicted in the raster image by comparing pixel ranks assigned to pixels in the region including the first pixel rank and the second pixel rank (¶ 0062: In step 410, a window is slid over the image to be analyzed. The window may be slid over the entire image or over only a part of the image. In step 420, YUV-histograms are generated for each or some of the window positions. Then, in step 430, it is evaluated for each or some of the window positions where a YUV-histogram was generated whether this window position represents a possible barcode pixel (in some embodiments; a group of possible barcode pixels).; ¶ 0065: In some embodiments, the example algorithm described in connection to FIG. 4 aims at finding areas that vary substantially between black and white. An alternative approach may be to look for high gradients in the image.; ¶ 0066: Some embodiments employing this alternative focus on features of the code structure, and explore the intensity contrast between pixels in a code.; Examiner’s note: Soderberg discloses a process by which adjacent pixel YUV values are compared to determine areas of substantial variances in the values (between black and white, or high gradient as disclosed in 0065). This is understood by the examiner to read on this claim limitation of determining an edge strength for an edge based on a comparison of the pixel ranks between a first and second pixel.).
Soderberg is considered to be analogous art as it pertains to edge detection in images. Therefore, it would have been obvious to one of ordinary skill in the art to combine the method for image processing (as taught by Takasu) and the method for retrieving information comprised in a barcode (as taught by Soderberg) before the effective filing date of the claimed invention. The motivation for this combination of references would be the method of Soderberg utilizes an algorithm that is not dependent on a single threshold, making sensitive solutions where it is difficult to find the correct threshold can depend on many thresholds, thus making the algorithm more robust and stable (See ¶ 0070).
Additionally, Peterson teaches a raster image (Col. 2, Line 48 – 50: In some cases, the edge map includes digital representation of the edges in the raster image, such as a bitmap.).
Peterson is considered to be analogous art as it pertains to raster image processing and edge detection. Therefore, it would have been obvious to one of ordinary skill in the art to combine the image processing apparatus (as taught by Takasu) and the content aware tracing for generative vector drawings (as taught by Peterson) before the effective filing date of the claimed invention. The motivation for this combination of references would be the method of Peterson reduces the overall number of user interactions required to produce a vector drawing by intelligently determining an edge being selected by a user (See Col 5 line 65 – Col 6 Line 3).
This motivation for the combination of Takasu, Soderberg, and Peterson is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. MPEP 2141 (III).
Regarding claim 2, the Takasu, Soderberg, and Peterson combination teaches the method of claim 1.
Additionally, Takasu teaches wherein determining the local histogram ranking of the pixels comprises:
splitting the raster image into color channels that indicate channel-specific pixel values for the pixels located in the sliding pixel window (¶ 0057: In particular, the CPU 310 converts the RGB value in each of the pixels in the subject image data being RGB-image data, to a brightness value. The brightness value may be, for example, a value in 256 scale between O and 255. A known formula to convert the RGB values to the brightness values may be used.; Examiner’s note: Under broadest reasonable interpretation, the examiner is interpreting this to mean any form of conversion on the image so as to create pixel data that can be ranked in the histogram. As color channels is not defined in the claim, transitioning the image from RBG to a brightness value is understood to be a “splitting of the raster image into color channels”.); and
determining channel-specific rankings of the pixels according to the channel-specific pixel values (Figure 10B; ¶ 0089: The histogram of the smaller block LBa in FIG. 10B includes a first mountain portion MP1a corresponding to the base-color part BS and a second mountain portion MP2a corresponding to the edges LE of the contour… however, when the smaller blocks SB does include the edges LE of the contours, an occupation rate of a number of pixels of the edges LE of the contours over a number of entire pixels in the smaller block SB may be relatively high.; ¶ 0091: In contrast, the smaller block SBa shown in FIG. 8B includes the edges LE of the contour; therefore, an average value Aa of the smaller block SBa in the histogram shown in FIG. 10B is shifted closer to the peak Pk2a from the peak Pk1a of the first mountain portion MP1a.).
Regarding claim 3, the Takasu, Soderberg, and Peterson combination teaches the method of claim 2.
Additionally, Takasu teaches wherein determining the edge strength for the edge depicted in the raster image comprises:
determining channel-specific edge strengths for the color channels by comparing channel- specific pixel ranks indicated by the channel-specific rankings of the pixels (¶ 0065: In S435, the CPU 310 calculates a sum T of the brightness values of the K pixels in the marked smaller block. In S440, the CPU 310 determines whether a difference { (M*N)-T} between a value (M*N), which is the median value M of the marked larger block multiplied by the number of pixels Nin the marked smaller block, and the sum T of the brightness values in the marked smaller block is greater than a predetermined threshold TH.; ¶ 0066: If the difference { (M*N)-T} is greater than the threshold TH (S440: YES), in S445, the CPU 310 determines that the marked smaller block is a local edge region.); and
combining channel-specific edge strengths into the edge strength for the edge depicted in the raster image (¶ 0072: As may be understood from the above description, when at least one of the smaller blocks SB, among a specific smaller block SB corresponding to a specific pixel P in the local edge region image AI and all of the smaller blocks SB that overlap the specific smaller block SB, is determined as the local edge region in S445, the specific smaller block SB is determined conclusively as the local edge region.).
Regarding claim 4, the Takasu, Soderberg, and Peterson combination teaches the method of claim 1.
Additionally, Takasu teaches further comprising:
generating the local histogram ranking of the pixels by using the pixel rank histogram that indicates ranking bins corresponding to the pixel values within the sliding pixel window (Figure 10A – 10C; Examiner’s note: The “ranking bin” under broadest reasonable interpretation is understood to be any category in which the value of a pixel falls within. Per Fig. 10A- 10C, is understood to comprise 256 bins, (incrementing from 0 – 255) where each pixel value is ranked and stored.); and
updating the pixel rank histogram to indicate additional pixel values for different locations of the sliding pixel window within the raster image (Figure 8B and 10A “Histogram in Larger Block”; ¶ 0087: FIGS. 10A-10C are illustrative views of histograms. FIG. 10A shows a histogram of the larger block LB shown in FIG. 8B.; Examiner’s note: The histogram of the larger block is a culmination of all pixels across the image which has been dissected into the 9 image areas of figure 8B. It is therefore a representation of the pixel rank histogram of claim 1 which also indicates additional pixels across the various image sections.).
Regarding claim 5, the Takasu, Soderberg, and Peterson combination teaches the method of claim 1.
Takasu does not explicitly teach wherein providing the edge for display comprises generating a vector image from the raster image by using a tracing model that converts the edge depicted in the raster image to a vector path.
However, Peterson does teach wherein providing the edge for display comprises generating a vector image from the raster image by using a tracing model that converts the edge depicted in the raster image to a vector path (Figure 1, 2; Col. 6, Line 13 – 19: In some implementations, the image conversion system 200 performs an edge validation check to determine whether a detected edge point belongs to a same edge as a previous edge point determined for the user interaction. Once a path along one or more edges of the raster image 201 is traced, accumulated edge points along the path can be used to generate a vector drawing 207.).
Peterson is considered to be analogous art as it pertains to raster image processing and edge detection. Therefore, it would have been obvious to one of ordinary skill in the art to combine the image processing apparatus (as taught by Takasu) and the content aware tracing for generative vector drawings (as taught by Peterson) before the effective filing date of the claimed invention. The motivation for this combination of references would be the method of Peterson reduces the overall number of user interactions required to produce a vector drawing by intelligently determining an edge being selected by a user (See Col 5 line 65 – Col 6 Line 3).
Regarding claim 7, the Takasu, Soderberg, and Peterson combination teaches the method of claim 1.
Additionally Takasu teaches determining one or more additional edges depicted in the raster image according to the pixel ranks indicated by the local histogram ranking of the pixels (Figure 10A – 10C; ¶ 0087: FIGS. 10A-10C are illustrative views of histograms. FIG. 10A shows a histogram of the larger block LB shown in FIG. 8B. FIG. l0B shows a histogram of the smaller block SBa shown in FIG. 8B. FIG. 10C shows a histogram of the smaller block SBb shown in FIG. 8B. The histograms shown in FIGS. 10A-10B are graphs with the horizontal axis indicating the brightness value and the vertical axis indicating a number of pixels included in each class of the brightness values.; ¶ 0088: The edges LE of the contours are in a single color forming thin and dark shadows; therefore, the brightness values in the edges LE may be substantially lower than the base-color part BS.; Examiner’s note: Takasu teaches a method of identifying edges in a sub-image using the values of peaks in the histogram. It is understood that a plurality of peaks below the average pixel value, or a larger peak below the average pixel value would indicate a plurality of edges in the sub-image.)
Additionally, Peterson teaches further comprising:
determining one or more additional edges depicted in the raster image according to the pixel ranks (Col. 8, Line 58 – 64: In some examples, the edge map can include a first value (e.g., a value of 0) for points of the edge map corresponding to pixels of the raster image 201 that do not belong to an edge (referred to herein as a non-edge pixels) and a second value ( e.g., a value of 1) for points of the edge map corresponding to pixels of the raster image 201 that are part of an edge (referred to herein as edge pixels).);
determining granularity levels associated with the edge and the one or more additional edges (Col. 8, Line 37 – 43: when generating the edge map, edge detection engine 202 can ensure that detected edges in the raster image 201 are represented as single-pixel-wide (I-pixel wide) lines in the edge map. In some instances, the edge detection engine 202 can represent a thicker line or shape in the raster image 201 (e.g., a line or shape that is at least three-pixels wide) using multiple single-pixel-wide lines.; Examiner’s note: As granularity is not defined in the claim, nor is the process of determining granularity levels, the examiner is interpreting this to mean the system merely accounts for the “granularity” of each edge. As Peterson ensures the edges are single-pixel-wide lines, this is understood to be a form of determining granularity levels for the edge.); and
generating a hierarchical contour for the raster image by arranging the edge and the one or more additional edges in a stratified structure according to the granularity levels (Col. 8, Line 43 – 51: When a thicker line or shape is depicted in the raster image 201, the edge detection engine 202 can identify multiple edges associated with the line or shape ( e.g., a shape with an inner edge and an outer edge or a line with two outer edges). For example, if a border around a raster element in the raster image 201 is thicker, the edge detection engine 202 can detect an outer single-pixel wide line and an inner single-pixel-wide line in the corresponding edge map.).
Peterson is considered to be analogous art as it pertains to raster image processing and edge detection. Therefore, it would have been obvious to one of ordinary skill in the art to combine the image processing apparatus (as taught by Takasu) and the content aware tracing for generative vector drawings (as taught by Peterson) before the effective filing date of the claimed invention. The motivation for this combination of references would be the method of Peterson reduces the overall number of user interactions required to produce a vector drawing by intelligently determining an edge being selected by a user (See Col 5 line 65 – Col 6 Line 3).
The rejection of method claim 1 above applies mutatis mutandis to the corresponding limitations of device claim 21 while noting that the rejection above cites to both method and device disclosures.
For the device limitations of claim 21 see Takasu’s teaching on:
One or more memory devices (¶ 0006: According to an aspect of the present disclosure, a non-transitory computer readable storage medium storing computer readable instructions that are executable by a computer is provided); and
One or more processors coupled to the one or more memory devices that cause the system to perform operations comprising (¶ 0006: According to an aspect of the present disclosure, a non-transitory computer readable storage medium storing computer readable instructions that are executable by a computer is provided)…
The rejection of method claim 2 above applies mutatis mutandis to the corresponding limitations of device claim 22 while noting that the rejection above cites to both method and device disclosures.
The rejection of method claim 2 above applies mutatis mutandis to the corresponding limitations of device claim 23 while noting that the rejection above cites to both method and device disclosures.
Regarding claim 24, the Takasu, Soderberg, and Peterson combination teaches the system of claim 21.
Additionally, Takasu teaches wherein the operations further comprise updating the pixel rank histogram to indicate additional pixel values for different locations of the sliding pixel window within the raster image (Figure 8B and 10A “Histogram in Larger Block”; ¶ 0087: FIGS. 10A-10C are illustrative views of histograms. FIG. 10A shows a histogram of the larger block LB shown in FIG. 8B.; Examiner’s note: The histogram of the larger block is a culmination of all pixels across the image which has been dissected into the 9 image areas of figure 8B. It is therefore a representation of the pixel rank histogram of claim 1 which also indicates additional pixels across the various image sections.).
The rejection of method claim 5 above applies mutatis mutandis to the corresponding limitations of device claim 25 while noting that the rejection above cites to both method and device disclosures.
The rejection of method claim 7 above applies mutatis mutandis to the corresponding limitations of device claim 27 while noting that the rejection above cites to both method and device disclosures.
The rejection of method claim 1 above applies mutatis mutandis to the corresponding limitations of manufacture claim 28 while noting that the rejection above cites to both method and manufacture disclosures.
For the manufacture limitations of claim 28 see Takasu’s teaching on:
A non-transitory computer-readable medium storing instructions, that when executed by one or more processors, cause a computing system to perform operations comprising (¶ 0006: According to an aspect of the present disclosure, a non-transitory computer readable storage medium storing computer readable instructions that are executable by a computer is provided)…
The rejection of method claim 2 above applies mutatis mutandis to the corresponding limitations of manufacture claim 29 while noting that the rejection above cites to both method and manufacture disclosures.
The rejection of method claim 3 above applies mutatis mutandis to the corresponding limitations of manufacture claim 30 while noting that the rejection above cites to both method and manufacture disclosures.
The rejection of device claim 24 above applies mutatis mutandis to the corresponding limitations of manufacture claim 31 while noting that the rejection above cites to both device and manufacture disclosures.
The rejection of method claim 7 above applies mutatis mutandis to the corresponding limitations of manufacture claim 33 while noting that the rejection above cites to both method and manufacture disclosures.
Claims 6, 26, and 32 are rejected under 35 U.S.C. 103 as being unpatentable over Takasu et al (U.S. Patent Publication No. 2022/0189035 A1, hereinafter “Takasu”) in view of Soderberg et al (U.S. Patent Publication No. 2011/0007967 A1, hereinafter “Soderberg) and further in view of Peterson et al (U.S. Patent No. 10,930,033, hereinafter “Peterson”) and Kwant et al (U.S. Patent Publication No. 2019/0035101 A1, “Kwant”).
Regarding claim 6, the Takasu, Soderberg, and Peterson combination teaches the method of claim 1.
Additionally Takasu and Peterson teach further comprising:
detecting object contours for an object depicted in a raster image (Takasu ¶ 0075: FIG. 6B shows that parts, in which the contours of the garment Ss and the chest pocket PCs are located, may more likely be determined as the local edge regions Ea, while parts, in which minute forms alone such as the fabric grains in the garment Ss are located, may less likely be determined as the local edge region Ea. ; Peterson Col. 21, Line 7 – 10: Based on the position of the cursor 648 with respect to the raster image 644, the image conversion system 200 can identify a detected edge within the edge map 650.)
determining the edge depicted in the raster image by superimposing the object contours for the object onto an edge map indicated by the pixel ranks (Col. 21, Line 43 – 51: Upon identifying a detected edge pixel, the image conversion system 200 can begin to generate a pixel line for the detected edge 652. For example, as shown in FIG. 6C, the detected and in some cases validated edge pixels of the edge 652 can be highlighted or otherwise emphasized (e.g., using one or more colors, weights, thicknesses, and/or patterns to contrast the pixel line 653 with the raster image 644) for display over the edge 652 as a pixel line 653 in the raster image 644.).
Peterson is considered to be analogous art as it pertains to raster image processing and edge detection. Therefore, it would have been obvious to one of ordinary skill in the art to combine the image processing apparatus (as taught by Takasu) and the content aware tracing for generative vector drawings (as taught by Peterson) before the effective filing date of the claimed invention. The motivation for this combination of references would be the method of Peterson reduces the overall number of user interactions required to produce a vector drawing by intelligently determining an edge being selected by a user (See Col 5 line 65 – Col 6 Line 3).
Takasu does not explicitly teach detecting object contours for an object depicted in a raster image utilizing a segmentation neural network.
However, Kwant does teach detecting object contours for an object depicted in a raster image utilizing a segmentation neural network (¶ 0028: FIG. 1 is a diagram of a system capable of detecting object contours using a cursor recurrent neural network, according to one embodiment.).
Kwant is considered to be analogous art as it pertains to image segmentation and edge detection. Therefore, it would have been obvious to one of ordinary skill in the art to combine the image processing apparatus (as taught by Takasu) and the method of real-time object detection using a cursor recurrent neural network (as taught by Kwant) before the effective filing date of the claimed invention. The motivation for this combination of references would be the method of Kwant applies a grid-based approach which divides an image into grid cells and processes each cell independently by an assigned neuron or node of the neural network. This improves the performance of parametric representations of lines (See ¶ 0036 - 0038).
This motivation for the combination of Takasu, Soderberg, Peterson, and Kwant is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. MPEP 2141 (III).
The rejection of method claim 6 above applies mutatis mutandis to the corresponding limitations of device claim 26 while noting that the rejection above cites to both method and device disclosures.
The rejection of method claim 6 above applies mutatis mutandis to the corresponding limitations of manufacture claim 32 while noting that the rejection above cites to both method and manufacture disclosures.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Arbelaez et al (P. Arbeláez, M. Maire, C. Fowlkes and J. Malik, "Contour Detection and Hierarchical Image Segmentation," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 5, pp. 898-916, May 2011, doi: 10.1109/TPAMI.2010.161.) teaches a system for segmentation and contour detection which determines contours in an image by taking histograms of intensity values of the input image and uses image discontinuities to detect contours.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDREW JONES whose telephone number is (703)756-4573. The examiner can normally be reached Monday - Friday 8:00-5:00 EST, off Every Other Friday.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Matthew Bella can be reached at (571) 272-7778. 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.
/ANDREW B. JONES/Examiner, Art Unit 2667
Prosecution Insights