DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application is being examined under the pre-AIA first to invent provisions.
Information Disclosure Statement
The information disclosure statement(s) (IDS) submitted on 05/30/2025 and 02/27/2026 is/are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement(s) is/are being considered by the examiner.
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 taught 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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (CN 113962882) (hereinafter Zhang) in view of Lin et al. (“A Multi-Feature Fusion Convolution Neural Network,” IEEE, 2021) (hereinafter Lin), further in view of Gillis (US 20230247205) (hereinafter Gillis).
Regarding claim 1, Zhang teaches performing feature extraction on a compressed image to obtain a compression feature map of the compressed image; performing reconstruction on the compression feature map to obtain a reconstruction feature map of the compressed image; performing quality factor (QF) prediction on the compression feature map to obtain a QF of the compressed image (see Zhang paragraphs 8-25 regarding extracting features on a compressed image to obtain a compression feature map, and a restoration of a compression feature map, and QF prediction using a neural network to obtain a QF of a compressed image, where both the extraction and restoration network has a plurality of cascading convolutional layers that respectively perform downsampling/encoding or upsampling/decoding with N and M recursive modules where the output of a first result input into the next layer until a last layer for ith encodings and jth decodings); and
However, Zhang does not explicitly teach denoising as needed for the limitations of claim 1.
Lin, in a similar field of endeavor, teaches generating a denoised compressed image having compression noise reduced or removed from the compressed image by performing denoising on the reconstruction feature map based on the QF (see Lin section 2 parts A-C regarding application of QF neural network feature map results being applied to denoising of compressed images based on QF and Introduction regarding multiple fusion modules at the beginning, between, and end of network layers so that cross-layer connection of features may be fused- in combination with Zhang , the cascading network and feature map and QF of Zhang may be used for denoising a compressed image based on QF and in the plurality of layers, fusion may occur by cross-layer connections with results cascade output by fusion result).
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the application to modify Zhang to include the teaching of Lin so that in combination with Zhang , the cascading network and feature map and QF of Zhang may be used for denoising a compressed image based on QF and in the plurality of layers, fusion may occur by cross-layer connections with results cascade output by fusion result.
One would be motivated to combine these teachings in order to improve the quality of compressed images (see Lin section 2 parts A-C).
However, the combination of Zhang and Lin does not explicitly teach an electronic device as needed for the limitations of claim 1.
Gillis, in a similar field of endeavor, teaches An image processing method, for an electronic device (see Gillis paragraph 19 regarding electronic device with processor and memory with instructions- in combination with Zhang and Lin, the method of Zhang and Lin may be executed by the device of Gillis) comprising:
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the application to modify the combination of Zhang and Lin to include the teaching of Gillis so that in combination with Zhang and Lin, the method of Zhang and Lin may be executed by the device of Gillis.
One would be motivated to combine these teachings in order to provide a device with which to implement the method of Zhang and Lin (see Gillis paragraph 19).
Regarding claim 2, the combination of Zhang, Lin, and Gillis teaches all aforementioned limitations of claim 1, and is analyzed as previously discussed.
Furthermore, the combination of Zhang, Lin, and Gillis teaches wherein the performing feature extraction comprises calling an extraction network, and performing downsampling and encoding on the compressed image via the extraction network, to obtain the compression feature map, and wherein the performing reconstruction comprises calling a reconstruction network, and performing upsampling and decoding on the compression feature map via the reconstruction network, to obtain the reconstruction feature map (see Zhang paragraphs 8-25 regarding extracting features on a compressed image to obtain a compression feature map, and a restoration of a compression feature map, and QF prediction using a neural network to obtain a QF of a compressed image, where both the extraction and restoration network has a plurality of cascading convolutional layers that respectively perform downsampling/encoding or upsampling/decoding with N and M recursive modules where the output of a first result input into the next layer until a last layer for ith encodings and jth decodings).
Regarding claim 3, the combination of Zhang, Lin, and Gillis teaches all aforementioned limitations of claim 2, and is analyzed as previously discussed.
Furthermore, the combination of Zhang, Lin, and Gillis teaches wherein the extraction network comprises a plurality of cascaded encoding layers, and wherein the performing downsampling and encoding comprises: performing downsampling and encoding on the compressed image via a first encoding layer of the plurality of cascaded encoding layers; outputting a first encoding result of the first encoding layer to a subsequent cascaded encoding layer, and further performing the downsampling and encoding and the outputting of the first encoding result via the subsequent cascaded encoding layer until a last encoding layer; and using a second encoding result output by the last encoding layer as the compression feature map (see Zhang paragraphs 8-25 regarding extracting features on a compressed image to obtain a compression feature map, and a restoration of a compression feature map, and QF prediction using a neural network to obtain a QF of a compressed image, where both the extraction and restoration network has a plurality of cascading convolutional layers that respectively perform downsampling/encoding or upsampling/decoding with N and M recursive modules where the output of a first result input into the next layer until a last layer for ith encodings and jth decodings).
Regarding claim 4, the combination of Zhang, Lin, and Gillis teaches all aforementioned limitations of claim 3, and is analyzed as previously discussed.
Furthermore, the combination of Zhang, Lin, and Gillis teaches wherein an ith encoding layer of the plurality of cascaded encoding layers comprises a first plurality of cascaded convolutional layers and a first downsampling layer, wherein the further performing the downsampling and encoding comprises: performing cascaded convolution on a third encoding result output by an (i-1)th encoding layer via the first plurality of cascaded convolutional layers in the ith encoding layer, to obtain a first convolution feature map; and performing downsampling on the first convolution feature map via the first downsampling layer in the ith encoding layer, to obtain a fourth encoding result of the ith encoding layer, and outputting the fourth encoding result of the ith encoding layer to an (i+1)th encoding layer, and wherein i is an increasing positive integer such that 1<i< N, and N is a total quantity of encoding layers (see Zhang paragraphs 8-25 regarding extracting features on a compressed image to obtain a compression feature map, and a restoration of a compression feature map, and QF prediction using a neural network to obtain a QF of a compressed image, where both the extraction and restoration network has a plurality of cascading convolutional layers that respectively perform downsampling/encoding or upsampling/decoding with N and M recursive modules where the output of a first result input into the next layer until a last layer for ith encodings and jth decodings).
Regarding claim 5, the combination of Zhang, Lin, and Gillis teaches all aforementioned limitations of claim 3, and is analyzed as previously discussed.
Furthermore, the combination of Zhang, Lin, and Gillis teaches wherein the reconstruction network comprises a plurality of cascaded decoding layers, and wherein the performing upsampling and decoding comprises: performing upsampling and decoding on the compression feature map via a first decoding layer of the plurality of cascaded decoding layers; outputting a first decoding result of the first decoding layer to a subsequent cascaded decoding layer, and further performing the upsampling and decoding and the outputting of the first decoding result via the subsequent cascaded decoding layer until a last decoding layer; and using a second decoding result output by the last decoding layer as the reconstruction feature map (see Zhang paragraphs 8-25 regarding extracting features on a compressed image to obtain a compression feature map, and a restoration of a compression feature map, and QF prediction using a neural network to obtain a QF of a compressed image, where both the extraction and restoration network has a plurality of cascading convolutional layers that respectively perform downsampling/encoding or upsampling/decoding with N and M recursive modules where the output of a first result input into the next layer until a last layer for ith encodings and jth decodings).
Regarding claim 6, the combination of Zhang, Lin, and Gillis teaches all aforementioned limitations of claim 5, and is analyzed as previously discussed.
Furthermore, the combination of Zhang, Lin, and Gillis teaches wherein a jth decoding layer of the plurality of cascaded decoding layers comprises a first plurality of cascaded convolutional layers and a first upsampling layer, and wherein the further performing the upsampling and decoding comprises: performing cascaded convolution on a first decoding result output by a (j-1)th decoding layer via the first plurality of cascaded convolutional layers in the jth decoding layer, to obtain a convolution feature map; and performing upsampling on the convolution feature map via the first upsampling layer in the jai decoding layer, to obtain a third decoding result of the jth decoding layer, and outputting the third decoding result of the jth decoding layer to a (j+l)th decoding layer, wherein j is an increasing positive integer such that 1<j< M, and M is a total quantity of decoding layers (see Zhang paragraphs 8-25 regarding extracting features on a compressed image to obtain a compression feature map, and a restoration of a compression feature map, and QF prediction using a neural network to obtain a QF of a compressed image, where both the extraction and restoration network has a plurality of cascading convolutional layers that respectively perform downsampling/encoding or upsampling/decoding with N and M recursive modules where the output of a first result input into the next layer until a last layer for ith encodings and jth decodings).
Regarding claim 7, the combination of Zhang, Lin, and Gillis teaches all aforementioned limitations of claim 5, and is analyzed as previously discussed.
Furthermore, the combination of Zhang, Lin, and Gillis teaches further comprising: performing denoising on a plurality of decoding results output by the plurality of cascaded decoding layers based on the QF, to obtain a plurality of denoised decoding results, and using the plurality of denoised decoding results as an input of a next decoding layer (see Lin section 2 parts A-C regarding application of QF neural network feature map results being applied to denoising of compressed images based on QF and Introduction regarding multiple fusion modules at the beginning, between, and end of network layers so that cross-layer connection of features may be fused- in combination with Zhang , the cascading network and feature map and QF of Zhang may be used for denoising a compressed image based on QF and in the plurality of layers, fusion may occur by cross-layer connections with results cascade output by fusion result).
One would be motivated to combine these teachings in order to improve the quality of compressed images (see Lin section 2 parts A-C).
Regarding claim 8, the combination of Zhang, Lin, and Gillis teaches all aforementioned limitations of claim 5, and is analyzed as previously discussed.
Furthermore, the combination of Zhang, Lin, and Gillis teaches wherein a plurality of cross-layer connection exists between the plurality of cascaded encoding layers and the plurality of cascaded decoding layers (see Lin section 2 parts A-C regarding application of QF neural network feature map results being applied to denoising of compressed images based on QF and Introduction regarding multiple fusion modules at the beginning, between, and end of network layers so that cross-layer connection of features may be fused- in combination with Zhang , the cascading network and feature map and QF of Zhang may be used for denoising a compressed image based on QF and in the plurality of layers, fusion may occur by cross-layer connections with results cascade output by fusion result), and
wherein the performing upsampling and decoding on the compression feature map comprises: performing upsampling and decoding on the compression feature map via the first decoding layer (see Zhang paragraphs 8-25 regarding extracting features on a compressed image to obtain a compression feature map, and a restoration of a compression feature map, and QF prediction using a neural network to obtain a QF of a compressed image, where both the extraction and restoration network has a plurality of cascading convolutional layers that respectively perform downsampling/encoding or upsampling/decoding with N and M recursive modules where the output of a first result input into the next layer until a last layer for ith encodings and jth decodings);
fusing a second decoding result of the upsampling and decoding and a third encoding result output by an encoding layer that has a first cross-layer connection with a second decoding layer, and outputting a third decoding result based on a fusion result of a subsequent cascaded decoding layer; further performing the upsampling and decoding, the fusing the second decoding result, and the outputting of the third decoding result; and using a fourth decoding result output by the last decoding layer as the reconstruction feature map (see Lin section 2 parts A-C regarding application of QF neural network feature map results being applied to denoising of compressed images based on QF and Introduction regarding multiple fusion modules at the beginning, between, and end of network layers so that cross-layer connection of features may be fused- in combination with Zhang , the cascading network and feature map and QF of Zhang may be used for denoising a compressed image based on QF and in the plurality of layers, fusion may occur by cross-layer connections with results cascade output by fusion result).
One would be motivated to combine these teachings in order to improve the quality of compressed images (see Lin section 2 parts A-C).
Regarding claim 9, the combination of Zhang, Lin, and Gillis teaches all aforementioned limitations of claim 8, and is analyzed as previously discussed.
Furthermore, the combination of Zhang, Lin, and Gillis teaches further comprising: performing denoising on a plurality of final decoding output by the plurality of cascaded decoding layers based on the QF, to obtain a plurality of denoised decoding results, and using the plurality of denoised decoding results as an input of a next decoding layer (see Lin section 2 parts A-C regarding application of QF neural network feature map results being applied to denoising of compressed images based on QF and Introduction regarding multiple fusion modules at the beginning, between, and end of network layers so that cross-layer connection of features may be fused- in combination with Zhang , the cascading network and feature map and QF of Zhang may be used for denoising a compressed image based on QF and in the plurality of layers, fusion may occur by cross-layer connections with results cascade output by fusion result).
One would be motivated to combine these teachings in order to improve the quality of compressed images (see Lin section 2 parts A-C).
Regarding claim 10, the combination of Zhang, Lin, and Gillis teaches all aforementioned limitations of claim 1, and is analyzed as previously discussed.
Furthermore, the combination of Zhang, Lin, and Gillis teaches wherein the performing denoising on the reconstruction feature map comprises: performing modulation on the QF, to obtain a modulation factor corresponding to the QF; and performing denoising on the reconstruction feature map based on the modulation factor, to obtain the denoised compressed image (see Gillis paragraph 23 regarding quality factor modulation which produces a modulation factor- in combination with Zhang and Lin, the denoising process of Zhang and Lin may have an adaptively modulated quality factor).
One would be motivated to combine these teachings in order to provide a device with which to implement the method of Zhang and Lin for the sake of adjusting quality of compressed images (see Gillis paragraph 23).
Independent claim(s) 11 is/are analogous in scope to claim(s) 1, albeit regarding an image processing apparatus with a memory and processor and code as taught by Gillis paragraph 19, and is/are rejected according to the same reasoning.
Dependent claim(s) 12-19 is/are analogous in scope to claim(s) 2-9, and is/are rejected according to the same reasoning.
Independent claim(s) 20 is/are analogous in scope to claim(s) 1, albeit regarding a non-transitory computer readable medium with code and processor as taught by Gillis paragraph 19, and is/are rejected according to the same reasoning.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Matthew D Kim whose telephone number is (571)272-3527. The examiner can normally be reached Monday - Friday: 9:30am - 5:30pm EST.
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, Joseph Ustaris can be reached at (571) 272-7383. 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.
/MATTHEW DAVID KIM/Primary Examiner, Art Unit 2483
Prosecution Insights