DETAILED 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 .
Amendments
Applicant’s Amendment filed on 7/23/2026 has been entered and made of record.
Currently Pending claims: 1-20
Independent claims: 1 and 13
Amended claims: 1-9 and 13-20
Response to Arguments
This office action is responsive to Applicant’s Arguments/Remarks Made in an Amendment received on 7/23/2026.
Applicant’s arguments, see page 8, filed 7/23/2026, with respect to the claim interpretation under 35 U.S.C. §112(f) have been fully considered and are persuasive. The claim interpretation under 35 U.S.C. §112(f) has been withdrawn.
Applicant’s arguments, see pages 8-9, filed 7/23/2026, with respect to the rejections of claims 1-20 under 35 U.S.C. §112(b) have been fully considered and are persuasive. The rejections of claims 1-20 under 35 U.S.C. §112(b) have been withdrawn.
Applicant’s arguments, see pages 9-10, filed 7/23/2026, with respect to rejections of claims 1-20 under 35 U.S.C. §101 have been fully considered and are persuasive. In summary, the Applicant argues the steps of determining a valid size and dividing the reference image into a plurality of first auxiliary images according to the valid size are computer-executed processing operations. The Examiner agrees that these limitations recite specific steps to implement an algorithm for image classification rather than merely reciting an abstract idea on a generic computer. Therefore, the claims incorporate the abstract idea into a practical application. rejections of claims 1-20 under 35 U.S.C. §101 have been withdrawn.
Applicant's arguments, see pages 11-12, filed 7/23/2026, with respect to the rejections of claims 1-20 under 35 U.S.C. §103 have been fully considered but they are not persuasive.
Applicant argues, on page 12:
PNG
media_image1.png
316
758
media_image1.png
Greyscale
The Examiner respectfully disagrees. Jonsson discloses comparing corresponding image blocks between a first image and a reference image, as cited in the previous Office Action (¶0034, The method of motion segmentation may be applied to any two of the image frames in the sequence of image frames. The second image frame may be an image frame temporally preceding the first image frame, or a reference image frame. The reference image frame may be a background image or a generated image; ¶0035, The method further comprises the step of dividing a first image frame from the sequence of image frames into a plurality of image blocks; ¶0036, for each image block of the plurality of image blocks, the image block is compared against a corresponding reference image block of a second image frame from the sequence of image frames. In practice this means that the second image frame also is divided into corresponding reference image blocks). Therefore, Jonsson discloses that the reference image is divided into the same blocks as the original image. Jonsson also discloses determining the number of blocks from a variable number of blocks (¶0046, The division can be any suitable division resulting in new image blocks larger than one pixel. Preferably the image frames are divided into 2-10 image blocks). Therefore, the rejections of claims 1-7, 9-18, and 20 under 35 U.S.C. §103 are rejected using the same references cited previously, as necessitated by amendment. Claims 8 and 19 are rejected under a new ground of rejection with US 2022/0114736 to Jönsson et al., US 2023/0298351 to Lee et al., and US 2022/0092400 to Elron et al., as necessitated by amendment.
Claim Rejections - 35 USC § 103
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, 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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-2, 5, 7, 13-14, and 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Jönsson et al. (US 2022/0114736) (hereafter, “Jönsson”) in view of Lee et al. (US 2023/0298351) (hereafter, “Lee”).
Regarding claim 1, Jönsson discloses an image analysis method applied to an image analysis apparatus, the image analysis apparatus having an operation processor (¶0069, central processing unit 304) and a camera (¶0069, a camera 301), the camera being configured to acquire an original image (¶0034, acquiring a sequence of image frames from a camera) relevant to a surveillance environment (¶0026, run as a part of a surveillance system), the image analysis method comprising: the operation processor determining a valid size according to a plurality of second auxiliary images divided from the original image (¶0035, dividing a first image frame from the sequence of image frames into a plurality of image blocks; ¶0046, The division can be any suitable division resulting in new image blocks larger than one pixel. Preferably the image frames are divided into 2-10 image blocks. Examiner considers the plurality of image blocks from the first frame as the “plurality of second auxiliary images” and selecting the number of blocks as “determining a valid size”); the operation processor setting a range provided by the original image (¶0046, a predefined region such as a region of interest. Examiner considers the predefined region as a “range”) [as a reference image]; and the operation processor dividing the [reference] image into a plurality of first auxiliary images in accordance with the determined valid size (¶0036, for each image block of the plurality of image blocks, the image block is compared against a corresponding reference image block of a second image frame from the sequence of image frames. In practice this means that the second image frame also is divided into corresponding reference image blocks; ¶0046, Preferably the image frames are divided into 2-10 image blocks … set with a smaller block size. Examiner considers the reference image blocks as the “plurality of first auxiliary images”. Examiner notes that Jönsson discloses dividing an image, which can be applied to the reference image taught by Lee), so as to apply the plurality of first auxiliary images for an image analysis model to generate an image classification result (¶0036, For image blocks having a measure of dissimilarity less than a threshold it may be assumed that there is no or limited movement. … For image blocks having a measure of dissimilarity greater than the threshold it can be assumed that there is movement within the image block. ¶0052, The presently disclosed motion segmentation may produce a motion mask. Examiner considers the measure of dissimilarity as the “analysis model” and the motion mask as the “classification result”); wherein the determined valid size is set to make a number of the plurality of first auxiliary images be the same as a number of the plurality of second auxiliary images (¶0036, for each image block of the plurality of image blocks, the image block is compared against a corresponding reference image block of a second image frame from the sequence of image frames. In practice this means that the second image frame also is divided into corresponding reference image blocks. Since the blocks are matching between the first image and the reference image, the number of blocks must be the same).
However, Jönsson fails to explicitly disclose a reference image acquired by setting the range.
Lee teaches a reference image acquired by setting the range (¶0115, zoom into all the regions of interest and pass the cropped image).
Both Jönsson and Lee are analogous to the claimed invention because both are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the region of interest cropping of Lee into image division of Jönsson. The suggestion/motivation for doing so would have been to use more details in image analysis, as suggested by Lee at ¶0115, This approach allows the use of more of the data of the object of interest to “zoom” into details such as the writing on a product label.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee to obtain the invention as specified in claim 1.
Regarding claim 2, in which claim 1 is incorporated, Jönsson discloses wherein the operation processor is configured to directly define the range within the original image (¶0070, The system (300) further comprises a processing unit (303) in the form of a central processing unit (CPU) configured to perform the presently disclosed method of motion segmentation (305) on raw image data from the image sensor (302). The motion segmentation (305) provides a region of interest) [to set as the reference image].
However, Jönsson fails to explicitly disclose a reference image acquired by setting the range.
Lee teaches a reference image acquired by setting the range (¶0115, zoom into all the regions of interest and pass the cropped image).
Both Jönsson and Lee are analogous to the claimed invention because both are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the region of interest cropping of Lee into image division of Jönsson. The suggestion/motivation for doing so would have been to use more details in image analysis, as suggested by Lee at ¶0115, This approach allows the use of more of the data of the object of interest to “zoom” into details such as the writing on a product label.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee to obtain the invention as specified in claim 2.
Regarding claim 5, in which claim 1 is incorporated, Jönsson discloses wherein the operation processor is configured to utilize the valid size to divide the reference image into the plurality of first auxiliary images partly overlapped with each other, or utilize the valid size to divide the reference image into the plurality of first auxiliary images spaced from each other (¶0046, having gaps between the image blocks is not excluded as an option for the presently disclosed method of motion segmentation. Since the limitation is recited in the alternative, Examiner considers this citation to fully disclose the limitation).
Regarding claim 7, in which claim 1 is incorporated, Jönsson discloses wherein the operation processor is configured to apply the plurality of second auxiliary images for the image analysis model to decide a number of the plurality of second auxiliary images (¶0049, compute or extract an average pixel value for the image block being compared and compare against the average pixel value of the corresponding reference image block. ¶0054, the image blocks can then be prioritized such that the image blocks having the greatest measure of dissimilarity are selected for further division and iteration. Comparing blocks 1 to 1 implies the same number of blocks. Therefore, the block number determining step applies to both the first and second auxiliary images), and decide optimal solution of the valid size (¶0054, An alternative way of controlling the number of image blocks for further division is to adjust the threshold. In one embodiment the threshold is adjusted after each iteration based on the measure of dissimilarity for the pairs of image blocks. Examiner considers iteratively adjusting a threshold to be an optimization routine), and then divide the reference image via the decided valid size to decide the plurality of first auxiliary images (¶0054, the image blocks can then be prioritized such that the image blocks having the greatest measure of dissimilarity are selected for further division and iteration), so that the number of the plurality of first auxiliary images is the same as the number of the plurality of second auxiliary images (¶0049, compute or extract an average pixel value for the image block being compared and compare against the average pixel value of the corresponding reference image block. Comparing blocks 1 to 1 implies the same number of blocks).
Regarding claim 13, Jönsson discloses an image analysis apparatus, comprising: a camera configured to acquire an original image (¶0034, acquiring a sequence of image frames from a camera); and an operation processor electrically connected with the camera (CPU (304) is configured to … control settings of the image sensor (302) and/or camera (301)), and configured to determine a valid size according to a plurality of second auxiliary images divided from the original image (¶0035, dividing a first image frame from the sequence of image frames into a plurality of image blocks; ¶0046, The division can be any suitable division resulting in new image blocks larger than one pixel. Preferably the image frames are divided into 2-10 image blocks. Examiner considers the plurality of image blocks from the first frame as the “plurality of second auxiliary images” and selecting the number of blocks as “determining a valid size”), set a range provided by the original image (¶0046, a predefined region such as a region of interest. Examiner considers the predefined region as a “range”) [as a reference image], and divide the [reference] image into a plurality of first auxiliary images in accordance with the determined valid size (¶0036, for each image block of the plurality of image blocks, the image block is compared against a corresponding reference image block of a second image frame from the sequence of image frames. In practice this means that the second image frame also is divided into corresponding reference image blocks; ¶0046, Preferably the image frames are divided into 2-10 image blocks … set with a smaller block size. Examiner considers the reference image blocks as the “plurality of first auxiliary images”. Examiner notes that Jönsson discloses dividing an image, which can be applied to the reference image taught by Lee), so as to apply the plurality of first auxiliary images for an image analysis model to generate an image classification result (¶0036, For image blocks having a measure of dissimilarity less than a threshold it may be assumed that there is no or limited movement. … For image blocks having a measure of dissimilarity greater than the threshold it can be assumed that there is movement within the image block. ¶0052, The presently disclosed motion segmentation may produce a motion mask. Examiner considers the measure of dissimilarity as the “analysis model” and the motion mask as the “classification result”); wherein the determined valid size is set to make a number of the plurality of first auxiliary images be the same as a number of the plurality of second auxiliary images (¶0036, for each image block of the plurality of image blocks, the image block is compared against a corresponding reference image block of a second image frame from the sequence of image frames. In practice this means that the second image frame also is divided into corresponding reference image blocks. Since the blocks are matching between the first image and the reference image, the number of blocks must be the same).
However, Jönsson fails to explicitly disclose a reference image acquired by setting the range.
Lee teaches a reference image acquired by setting the range (¶0115, zoom into all the regions of interest and pass the cropped image).
Both Jönsson and Lee are analogous to the claimed invention because both are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the region of interest cropping of Lee into image division of Jönsson. The suggestion/motivation for doing so would have been to use more details in image analysis, as suggested by Lee at ¶0115, This approach allows the use of more of the data of the object of interest to “zoom” into details such as the writing on a product label.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee to obtain the invention as specified in claim 13.
Regarding claim 14, in which claim 13 is incorporated, Jönsson discloses wherein the operation processor is configured to directly define the range within the original image (¶0070, The system (300) further comprises a processing unit (303) in the form of a central processing unit (CPU) configured to perform the presently disclosed method of motion segmentation (305) on raw image data from the image sensor (302). The motion segmentation (305) provides a region of interest) [to set as the reference image].
However, Jönsson fails to explicitly disclose a reference image acquired by setting the range.
Lee teaches a reference image acquired by setting the range (¶0115, zoom into all the regions of interest and pass the cropped image).
Both Jönsson and Lee are analogous to the claimed invention because both are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the region of interest cropping of Lee into image division of Jönsson. The suggestion/motivation for doing so would have been to use more details in image analysis, as suggested by Lee at ¶0115, This approach allows the use of more of the data of the object of interest to “zoom” into details such as the writing on a product label.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee to obtain the invention as specified in claim 14.
Regarding claim 17, in which claim 13 is incorporated, Jönsson discloses wherein the operation processor is configured to utilize the valid size to divide the reference image into the plurality of first auxiliary images partly overlapped with each other, or utilize the valid size to divide the reference image into the plurality of first auxiliary images spaced from each other(¶0046, having gaps between the image blocks is not excluded as an option for the presently disclosed method of motion segmentation. Since the limitation is recited in the alternative, Examiner considers this citation to fully disclose the limitation).
Regarding claim 18, in which claim 13 is incorporated, Jönsson discloses wherein the operation processor is configured to apply the plurality of second auxiliary images for the image analysis model to decide a number of the plurality of second auxiliary images (¶0049, compute or extract an average pixel value for the image block being compared and compare against the average pixel value of the corresponding reference image block. ¶0054, the image blocks can then be prioritized such that the image blocks having the greatest measure of dissimilarity are selected for further division and iteration. Comparing blocks 1 to 1 implies the same number of blocks. Therefore, the block number determining step applies to both the first and second auxiliary images), and decide optimal solution of the valid size (¶0054, An alternative way of controlling the number of image blocks for further division is to adjust the threshold. In one embodiment the threshold is adjusted after each iteration based on the measure of dissimilarity for the pairs of image blocks. Examiner considers iteratively adjusting a threshold to be an optimization routine), and then divide the reference image via the decided valid size to decide the plurality of first auxiliary images (¶0054, the image blocks can then be prioritized such that the image blocks having the greatest measure of dissimilarity are selected for further division and iteration), so that the number of the plurality of first auxiliary images is the same as the number of the plurality of second auxiliary images (¶0049, compute or extract an average pixel value for the image block being compared and compare against the average pixel value of the corresponding reference image block. Comparing blocks 1 to 1 implies the same number of blocks).
Claims 3, 4, 15, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Jönsson et al. (US 2022/0114736) (hereafter, “Jönsson”) in view of Lee et al. (US 2023/0298351) (hereafter, “Lee”) as applied to claims 1 and 13 above, and further in view of Bakhshmand (US 2026/0105590).
Regarding claim 3, Jönsson in view of Lee discloses the image analysis method of claim 1.
However, neither Jönsson nor Lee, whether considered individually or in combination, disclose wherein the operation processor is configured to reduce the original image into an analysis image.
Bakhshmand teaches wherein the operation processor is configured to reduce the original image into an analysis image (¶0221, cropping size is equal to the input size of the classifier model 352, and cropped image 350a is generated. Examiner considers cropping an image to the input size as “reducing” the image).
Jönsson, Lee, and Bakhshmand are analogous to the claimed invention because all three are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the image reduction of into Bakhshmand into the region of interest cropping of Lee and the image division of Jönsson. The suggestion/motivation for doing so would have been to improve accuracy, as suggested by Bakhshmand at ¶0223, classification accuracy may be improved.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee and Bakhshmand.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee and Bakhshmand to obtain the invention as specified in claim 3.
Regarding claim 4, in which claim 3 is incorporated, Jönsson discloses wherein the operation processor is configured define the range within the analysis image to set as the reference image (¶0070, The system (300) further comprises a processing unit (303) in the form of a central processing unit (CPU) configured to perform the presently disclosed method of motion segmentation (305) on raw image data from the image sensor (302). The motion segmentation (305) provides a region of interest), and to divide the reference image into the plurality of first auxiliary images (¶0035, dividing a first image frame from the sequence of image frames into a plurality of image blocks), and [the image classification result is optimized when the plurality of first auxiliary images is applied for the image analysis model].
However, neither Jönsson nor Lee, whether considered individually or in combination, disclose the image classification result is optimized when the plurality of first auxiliary images is applied for the image analysis model.
Bakhshmand teaches the image classification result is optimized when the plurality of first auxiliary images is applied for the image analysis model (¶0223, adaptive cropping … classification accuracy may be improved. Without adaptive cropping, contextual information such as size and dimension ratio of cropped anomalies may be lost. Examiner considers improving classification accuracy to mean “optimized”).
Jönsson, Lee, and Bakhshmand are analogous to the claimed invention because all three are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the image reduction of into Bakhshmand into the region of interest cropping of Lee and the image division of Jönsson. The suggestion/motivation for doing so would have been to improve accuracy, as suggested by Bakhshmand at ¶0223, classification accuracy may be improved.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee and Bakhshmand.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee and Bakhshmand to obtain the invention as specified in claim 4.
Regarding claim 15, Jönsson in view of Lee discloses the image analysis apparatus of claim 13.
However, neither Jönsson nor Lee, whether considered individually or in combination, disclose wherein the operation processor is configured to reduce the original image into an analysis image.
Bakhshmand teaches wherein the operation processor is configured to reduce the original image into an analysis image (¶0221, cropping size is equal to the input size of the classifier model 352, and cropped image 350a is generated. Examiner considers cropping an image to the input size as “reducing” the image).
Jönsson, Lee, and Bakhshmand are analogous to the claimed invention because all three are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the image reduction of into Bakhshmand into the region of interest cropping of Lee and the image division of Jönsson. The suggestion/motivation for doing so would have been to improve accuracy, as suggested by Bakhshmand at ¶0223, classification accuracy may be improved.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee and Bakhshmand.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee and Bakhshmand to obtain the invention as specified in claim 15.
Regarding claim 16, in which claim 15 is incorporated, Jönsson discloses wherein the operation processor is configured to define the range within the analysis image to set as the reference image (¶0070, The system (300) further comprises a processing unit (303) in the form of a central processing unit (CPU) configured to perform the presently disclosed method of motion segmentation (305) on raw image data from the image sensor (302). The motion segmentation (305) provides a region of interest), and divide the reference image defined by the range within the analysis image into the plurality of first auxiliary images (¶0035, dividing a first image frame from the sequence of image frames into a plurality of image blocks), and [the image classification result is optimized when the plurality of first auxiliary images is applied for the image analysis model].
However, neither Jönsson nor Lee, whether considered individually or in combination, disclose the image classification result is optimized when the plurality of first auxiliary images is applied for the image analysis model.
Bakhshmand teaches the image classification result is optimized when the plurality of first auxiliary images is applied for the image analysis model (¶0223, adaptive cropping … classification accuracy may be improved. Without adaptive cropping, contextual information such as size and dimension ratio of cropped anomalies may be lost. Examiner considers improving classification accuracy to mean “optimized”).
Jönsson, Lee, and Bakhshmand are analogous to the claimed invention because all three are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the image reduction of Bakhshmand into the region of interest cropping of Lee and the image division of Jönsson. The suggestion/motivation for doing so would have been to improve accuracy, as suggested by Bakhshmand at ¶0223, classification accuracy may be improved.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee and Bakhshmand.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee and Bakhshmand to obtain the invention as specified in claim 16.
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Jönsson et al. (US 2022/0114736) (hereafter, “Jönsson”) in view of Lee et al. (US 2023/0298351) (hereafter, “Lee”) as applied to claim 1 above, and further in view of Motoki (US 2020/0104708).
Regarding claim 6, in which claim 1 is incorporated, Jönsson discloses wherein the operation processor is configured to divide the reference image into the plurality of first auxiliary images spaced from each other (¶0046, having gaps between the image blocks is not excluded as an option for the presently disclosed method of motion segmentation), and [the image classification result is not optimized when the plurality of first auxiliary images is applied for the image analysis model].
However, neither Jönsson nor Lee, whether considered individually or in combination, explicitly disclose the image classification result is not optimized when the plurality of first auxiliary images is applied for the image analysis model.
Motoki teaches the image classification result is not optimized when the plurality of first auxiliary images is applied for the image analysis model (¶0145, according to the trained model 920 with the autoregression module, the operations can be performed without influence due to a gap arising as a result of dividing the pre-processed image data).
Jönsson, Lee, and Motoki are analogous to the claimed invention because all three are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the gap mitigation of Motoki into the region of interest cropping of Lee and the image division of Jönsson. The suggestion/motivation for doing so would have been to use increased image context, as suggested by Motoki at ¶0116, phenomena at other positions in the same concatenated data can be reflected.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee and Motoki.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee and Motoki to obtain the invention as specified in claim 6.
Claims 8 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Jönsson et al. (US 2022/0114736) (hereafter, “Jönsson”) in view of Lee et al. (US 2023/0298351) (hereafter, “Lee”) as applied to claim 1 above, and further in view of Elron et al. (US 2022/0092400) (hereafter, “Elron”).
Regarding claim 8, in which claim 1 is incorporated, Jönsson discloses wherein the original image divided into the plurality of second auxiliary images (¶0035, dividing a first image frame from the sequence of image frames into a plurality of image blocks) is applied for the image analysis model to acquire the [image classification] result (¶0049, compute or extract an average pixel value for the image block), and the reference image divided into the plurality of first auxiliary images (¶0036, the second image frame also is divided into corresponding reference image blocks) is applied for the image analysis model to generate another [image classification] result different from the [image classification] result generated using the plurality of second auxiliary images (¶0049, According to one embodiment of the presently disclosed method of motion segmentation the measure of dissimilarity is a predefined measure of dissimilarity. One example is to compute or extract an average pixel value for the image block being compared and compare against the average pixel value of the corresponding reference image block. If the difference between the values is greater than a certain threshold the image can be categorized as a block with movement).
However, neither Jönsson nor Lee, whether considered individually or in combination, explicitly disclose an image classification result.
Elron discloses an image classification result (¶0025, An image 104 shows the difference in classifications (between background and foreground) between the two consecutive frames 100 and 102. Those light areas that are non-zero (in difference indicating motion) in image 104 are a very small part of the image and indicate the noticeable differences between the two frames).
Jönsson, Lee, and Elron are analogous to the claimed invention because all three are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the image classification result of Elron into the region of interest cropping of Lee and the image division of Jönsson. The suggestion/motivation for doing so would have been a simple substitution of the classification result of Elron for the image analysis results in the method of Jönsson. Both the Elron and Jönsson us their respective results to compare different images and both can be used to determine motion in the image. Therefore, one of ordinary skill in the art would have been able to perform the substitution with predictable results.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee and Elron.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee and Schindler to obtain the invention as specified in claim 8.
Regarding claim 19, in which claim 13 is incorporated, Jönsson discloses wherein the original image divided into the plurality of second auxiliary images (¶0035, dividing a first image frame from the sequence of image frames into a plurality of image blocks) is applied for the image analysis model to acquire the [image classification] result (¶0049, compute or extract an average pixel value for the image block), and the reference image divided into the plurality of first auxiliary images (¶0036, the second image frame also is divided into corresponding reference image blocks) is applied for the image analysis model to generate another [image classification] result different from the [image classification] result generated using the plurality of second auxiliary images (¶0049, According to one embodiment of the presently disclosed method of motion segmentation the measure of dissimilarity is a predefined measure of dissimilarity. One example is to compute or extract an average pixel value for the image block being compared and compare against the average pixel value of the corresponding reference image block. If the difference between the values is greater than a certain threshold the image can be categorized as a block with movement).
However, neither Jönsson nor Lee, whether considered individually or in combination, explicitly disclose an image classification result.
Elron discloses an image classification result (¶0025, An image 104 shows the difference in classifications (between background and foreground) between the two consecutive frames 100 and 102. Those light areas that are non-zero (in difference indicating motion) in image 104 are a very small part of the image and indicate the noticeable differences between the two frames).
Jönsson, Lee, and Elron are analogous to the claimed invention because all three are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the image classification result of Elron into the region of interest cropping of Lee and the image division of Jönsson. The suggestion/motivation for doing so would have been a simple substitution of the classification result of Elron for the image analysis results in the method of Jönsson. Both the Elron and Jönsson us their respective results to compare different images and both can be used to determine motion in the image. Therefore, one of ordinary skill in the art would have been able to perform the substitution with predictable results.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee and Elron.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee and Schindler to obtain the invention as specified in claim 19.
Claims 9, 10, 12, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Jönsson et al. (US 2022/0114736) (hereafter, “Jönsson”) in view of Lee et al. (US 2023/0298351) (hereafter, “Lee”) and Bakhshmand (US 2026/0105590) as applied to claims 3 and 15 above, and further in view of Steiner et al. (US 2025/0117893) (hereafter, “Steiner”).
Regarding claim 9, Jönsson in view of Lee and Bakhshmand discloses the image analysis method of claim 3.
However, none of Jönsson, Lee, or Bakhshmand, whether considered individually or in combination, explicitly disclose wherein the operation processor is configured to reduce the original image via a first preset ratio for generating the analysis image, and partly overlap two adjacent first auxiliary images of the plurality of first auxiliary images via a second preset ratio, a sum of the first preset ratio and the second preset ratio is greater than or equal to 1.
Steiner teaches wherein the operation processor is configured to reduce the original image via a first preset ratio for generating the analysis image (¶0076, A 1:1 patch 202 can be extracted at a native resolution), and partly overlap two adjacent first auxiliary images of the plurality of first auxiliary images via a second preset ratio (Fig. 4, top row; ¶0097, achieve a threshold proportion of overlap), a sum of the first preset ratio and the second preset ratio is greater than or equal to 1 (¶0076, A 1:1 patch. Since the ratio in Steiner is 1, all sums with it must be greater than or equal to 1).
Jönsson, Lee, Bakhshmand, and Steiner are analogous to the claimed invention because all are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the ratios of Steiner into the image reduction of Bakhshmand, the region of interest cropping of Lee, and the image division of Jönsson. The suggestion/motivation for doing so would have been to improve scalability and generalizability, as suggested by Steiner at ¶0055, the present disclosure provides improvements to the scalability and generalizability of machine-learned image processing models.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee, Bakhshmand, and Steiner.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee, Bakhshmand, and Steiner to obtain the invention as specified in claim 9.
Regarding claim 10, Jönsson in view of Lee, Bakhshmand, and Steiner discloses the image analysis method of claim 9.
However, none of Jönsson, Lee, or Bakhshmand, whether considered individually or in combination, explicitly disclose wherein the operation processor reducing the original image to generate the analysis image comprises: the operation processor utilizing a preset ratio to change a vertical size and a horizontal size of the original image to generate the analysis image.
Steiner teaches wherein the operation processor reducing the original image to generate the analysis image comprises: the operation processor utilizing a preset ratio to change a vertical size and a horizontal size of the original image to generate the analysis image (Fig. 2, #204; ¶0081, to emulate a lower magnification than the native magnification, a portion of the original image having a dimension larger than the input dimension can be resampled/regenerated to form an emulated lower magnification patch 204 that has dimension(s) aligned to the input dimension(s). Examiner considers the magnification to be a “ratio” and that aligning plurality of dimensions indicates both the “vertical” and “horizontal” sizes as illustrated in Fig. 2 #205).
Jönsson, Lee, Bakhshmand, and Steiner are analogous to the claimed invention because all are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the ratios of Steiner into the image reduction of Bakhshmand, the region of interest cropping of Lee, and the image division of Jönsson. The suggestion/motivation for doing so would have been to improve scalability and generalizability, as suggested by Steiner at ¶0055, the present disclosure provides improvements to the scalability and generalizability of machine-learned image processing models.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee, Bakhshmand, and Steiner.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee, Bakhshmand, and Steiner to obtain the invention as specified in claim 10.
Regarding claim 12, in which claim 9 is incorporated, Jönsson discloses wherein the operation processor reducing the original image to generate the analysis image comprises: the operation processor utilize a foreground detection technology to set a region of interest within the original image (¶0055, a region of interest may be handled different than a surrounding (background) region. Examiner considers separating the region of interest from the background to imply the ROI is in the foreground); and the operation processor setting a coverage range of the analysis image within the original image based on a center of the region of interest (¶0055, a central region of the image may be more important for the motion mask than peripheral regions. These areas may then be associated with a higher (or lower) priority).
Regarding claim 20, Jönsson in view of Lee and Bakhshmand discloses the image analysis apparatus of claim 15.
However, none of Jönsson, Lee, or Bakhshmand, whether considered individually or in combination, explicitly disclose wherein the operation processor is configured to reduce the original image via a first preset ratio for generating the analysis image, and partly overlap two adjacent first auxiliary images of the plurality of first auxiliary images via a second preset ratio, a sum of the first preset ratio and the second preset ratio is greater than or equal to 1.
Steiner teaches wherein the operation processor is configured to reduce the original image via a first preset ratio for generating the analysis image (¶0076, A 1:1 patch 202 can be extracted at a native resolution), and partly overlap two adjacent first auxiliary images of the plurality of first auxiliary images via a second preset ratio (Fig. 4, top row; ¶0097, achieve a threshold proportion of overlap), a sum of the first preset ratio and the second preset ratio is greater than or equal to 1 (¶0076, A 1:1 patch. Since the ratio in Steiner is 1, all sums with it must be greater than or equal to 1).
Jönsson, Lee, Bakhshmand, and Steiner are analogous to the claimed invention because all are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the ratios of Steiner into the image reduction of Bakhshmand, the region of interest cropping of Lee, and the image division of Jönsson. The suggestion/motivation for doing so would have been to improve scalability and generalizability, as suggested by Steiner at ¶0055, the present disclosure provides improvements to the scalability and generalizability of machine-learned image processing models.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee, Bakhshmand, and Steiner.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee, Bakhshmand, and Steiner to obtain the invention as specified in claim 20.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Jönsson et al. (US 2022/0114736) (hereafter, “Jönsson”) in view of Lee et al. (US 2023/0298351) (hereafter, “Lee”), Bakhshmand (US 2026/0105590), and Steiner et al. (US 2025/0117893) (hereafter, “Steiner”)as applied to claim 9 above, and further in view of Morris et al. (US 2022/0155007) (hereafter, “Morris”).
Regarding claim 11, Jönsson in view of Lee, Bakhshmand, and Steiner discloses the image analysis method of claim 9.
However, none of Jönsson, Lee, Bakhshmand, or Steiner, whether considered individually or in combination, explicitly disclose wherein the operation processor reducing the original image to generate the analysis image comprises: the operation processor computing a preset percentage of a pixel number difference between the original image and the analysis image in a horizontal direction, so as to define an interval between a vertical boundary of the analysis image and a related vertical boundary of the original image; and the operation processor computing the preset percentage of a pixel number difference between the original image and the analysis image in a vertical direction, so as to define an interval between a horizontal boundary of the analysis image and a related horizontal boundary of the original image.
Morris teaches wherein the operation processor reducing the original image to generate the analysis image comprises: the operation processor computing a preset percentage of a pixel number difference between the original image and the analysis image in a horizontal direction (¶0044, the dimensions of anchor boundary 182 may be increased by fixed percentage or dimension. In this regard, the width. Examiner considers width as the horizontal direction), so as to define an interval between a vertical boundary of the analysis image and a related vertical boundary of the original image (¶0044, increased by 20%, 40%, 50%, 60%, or greater); and the operation processor computing the preset percentage of a pixel number difference between the original image and the analysis image in a vertical direction (¶0044, the dimensions of anchor boundary 182 may be increased by fixed percentage or dimension. In this regard, … depth. Examiner considers width as the vertical direction), so as to define an interval between a horizontal boundary of the analysis image and a related horizontal boundary of the original image (¶0044, increased by 20%, 40%, 50%, 60%, or greater).
Jönsson, Lee, Bakhshmand, Steiner, and Morris are analogous to the claimed invention because all are in the field of image classification. It would have been obvious to a person of ordinary skill before the effective filing date of the claimed invention to incorporate the horizontal and vertical intervals of Morris into the ratios of Steiner, the image reduction of Bakhshmand, the region of interest cropping of Lee, and the image division of Jönsson. The suggestion/motivation for doing so would have been to improve efficiency, as suggested by Morris at ¶0046, detected while minimizing or reducing the necessary processing power, computer memory, or other computational resources.
This method of improving Jönsson was within the ordinary ability of one of ordinary skill in the art based on the teachings of Lee, Bakhshmand, Steiner, and Morris.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date, to modify Jönsson with the teachings of Lee, Bakhshmand, Steiner, and Morris to obtain the invention as specified in claim 11.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Greenway et al. (US 2017/0018065) discloses comparing patches between images to determine focus (¶0046, For determining if a video camera's level of focus has decreased over time, this approach has to be adjusted to use an image that is established as the reference to which all others are compared, even if images are separated vastly in terms of time of image capture).
Schindler et al. (US 2025/0095405) discloses comparing an image to reference patches for classification (¶0087, Based on the determined degrees of similarity between the extracted image patch from step 602 and the plurality of reference image patches arising from the classification established in the process 730).
Liu et al. (US 2021/0326624) discloses a determining a shared feature set between images (¶0058, the present invention provides a region feature alignment module to predict the offset transformation relationship between the reference modal and the sensing modal).
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to XIAOMAO DING whose telephone number is (571)272-7237. The examiner can normally be reached Mon-Fri 9:00-5:00.
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, Henok Shiferaw can be reached at (571) 272-4637. 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.
/XIAOMAO DING/Examiner, Art Unit 2676
/Henok Shiferaw/Supervisory Patent Examiner, Art Unit 2676
Prosecution Insights