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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 03/26/2025, 12/18/2025, and 01/13/2026 and has/have been considered by the examiner.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-15 of U.S. Patent No. 12243284 B2. Although the claims at issue are not identical, they are not patentably distinct from each other because Claims 1-20 of the instant application can be anticipated by the claims 1-15 of U.S. Patent No. 12243284 B2.
Instant Application 19062652
U.S. Patent No. 12243284 B2
1. An image classification method, comprising: obtaining an input feature map of a to-be-processed image; performing convolution processing on the input feature map based on M convolution kernels of a neural network to obtain an intermediate feature map comprising M channels, wherein M is a positive integer; performing convolution processing on the M channels of the intermediate feature map based on N matrices to obtain an output feature map comprising N channels, wherein the N matrices represent N convolution kernels, and N is a positive integer; and classifying the to-be-processed image based on the output feature map to obtain a classification result of the to-be-processed image.
2. The image classification method according to claim 1, wherein the N matrices comprise M groups of convolution kernels, and the M groups of convolution kernels respectively correspond to the M channels of the intermediate feature map, and wherein a quantity of channels of each of the N matrices is less than M, N is greater than M.
7. The image classification method according to claim 1, wherein performing the convolution processing on the M channels of the intermediate feature map based on N matrices to obtain an output feature map comprising N channels, comprises: performing matrix transformation on the M channels of the intermediate feature map based on the N matrices to obtain an output feature map comprising the N channels.
1. An image classification method, comprising: obtaining an input feature map of a to-be-processed image; performing convolution processing on the input feature map based on M convolution kernels of a neural network, to obtain an intermediate feature map comprising M channels, wherein M is a positive integer; performing convolution processing on the M channels of the intermediate feature map based on N matrices, to obtain an output feature map comprising N channels, wherein the N matrices represent N convolution kernels, the N matrices comprise M groups of convolution kernels, and the M groups of convolution kernels respectively correspond to the M channels of the intermediate feature map, and wherein a quantity of channels of each of the N matrices is less than M, N is greater than M, and N is a positive integer; and classifying the to-be-processed image based on the output feature map, to obtain a classification result of the to-be-processed image.
8. An image classification apparatus, comprising: one or more processors; and one or more memories coupled to the one or more processors and store programming instructions for execution by the one or more processors to: obtain an input feature map of a to-be-processed image; perform convolution processing on the input feature map based on M convolution kernels of a neural network to obtain an intermediate feature map comprising M channels, wherein M is a positive integer; perform convolution processing on the M channels of the intermediate feature map based on N matrices to obtain an output feature map comprising N channels, wherein the N matrices represent N convolution kernels, and N is a positive integer; and classify the to-be-processed image based on the output feature map to obtain a classification result of the to-be-processed image.
9. The image classification apparatus according to claim 8, wherein the N matrices comprise M groups of convolution kernels, and the M groups of convolution kernels respectively correspond to the M channels of the intermediate feature map, and wherein a quantity of channels of each of the N matrices is less than M, N is greater than M.
14. The image classification apparatus according to claim 8, wherein performing the convolution processing on the M channels of the intermediate feature map based on N matrices to obtain an output feature map comprising N channels, comprises: performing matrix transformation on the M channels of the intermediate feature map based on the N matrices to obtain an output feature map comprising the N channels.
6. An image classification apparatus, comprising: one or more processors; and one or more memories coupled to the one or more processors and store programming instructions for execution by the one or more processors to: obtain an input feature map of a to-be-processed image; perform convolution processing on the input feature map based on M convolution kernels of a neural network, to obtain an intermediate feature map comprising M channels, wherein M is a positive integer; perform convolution processing on the M channels of the intermediate feature map based on N matrices, to obtain an output feature map comprising N channels, wherein the N matrices represent N convolution kernels, the N matrices comprise M groups of convolution kernels, and the M groups of convolution kernels respectively correspond to the M channels of the intermediate feature map, and wherein a quantity of channels of each of the N matrices is less than M, N is greater than M, and N is a positive integer; and classify the to-be-processed image based on the output feature map, to obtain a classification result of the to-be-processed image.
15. A non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores one or more programming instructions for execution by one or more processors of a device to perform operations comprising: obtaining an input feature map of a to-be-processed image; performing convolution processing on the input feature map based on M convolution kernels of a neural network to obtain an intermediate feature map comprising M channels, wherein M is a positive integer; performing convolution processing on the M channels of the intermediate feature map based on N matrices to obtain an output feature map comprising N channels, wherein the N matrices represent N convolution kernels, and N is a positive integer; and classifying the to-be-processed image based on the output feature map to obtain a classification result of the to-be-processed image.
16. The non-transitory computer-readable storage medium according to claim 15, wherein the N matrices comprise M groups of convolution kernels, and the M groups of convolution kernels respectively correspond to the M channels of the intermediate feature map, and wherein a quantity of channels of each of the N matrices is less than M, N is greater than M.
11. A non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores one or more instructions that when executed by a device, cause the device to perform operations comprising: obtaining an input feature map of a to-be-processed image; performing convolution processing on the input feature map based on M convolution kernels of a neural network, to obtain an intermediate feature map comprising M channels, wherein M is a positive integer; performing convolution processing on the M channels of the intermediate feature map based on N matrices, to obtain an output feature map comprising N channels, wherein the N matrices represent N convolution kernels, the N matrices comprise M groups of convolution kernels, and the M groups of convolution kernels respectively correspond to the M channels of the intermediate feature map, and wherein a quantity of channels of each of the N matrices is less than M, N is greater than M, and N is a positive integer; and classifying the to-be-processed image based on the output feature map, to obtain a classification result of the to-be-processed image.
Other rejected dependent claims of instant application can be found basically word to word in corresponding dependent claims of U.S. Patent No. 12243284 B2.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1, 7-8, and 14-15 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Lecun et al (Proceedings of the IEEE, Vol. 86, No.11, pp. 2278-2324, 1998), hereinafter Lecun.
-Regarding claim 1, Lecun discloses an image classification method, comprising (Abstract; FIGS. 1-34; Page 2282, 2nd Col., Section II): obtaining an input feature map of a to-be-processed image (FIG. 2; Page 2283 2nd Col., line 19 – Page 2284, 1st Col, 1st paragraph); performing convolution processing on the input feature map based on M convolution kernels of a neural network to obtain an intermediate feature map comprising M channels, wherein M is a positive integer (FIG. 2, layers C1-S2; Page 2284, 2nd Col., Section B; Page 2313, 1st Col., Section B); performing convolution processing on the M channels of the intermediate feature map based on N matrices to obtain an output feature map comprising N channels, wherein the N matrices represent N convolution kernels, and N is a positive integer (FIG. 2, layer C3; Table 1; Page 2284, 2nd Col., Section B; Page 2313, 1st Col., Section B); and classifying the to-be-processed image based on the output feature map to obtain a classification result of the to-be-processed image (FIGS. 1-2, output layer; Page 2285, 2nd Col., 2nd paragraph).
-Regarding claim 8, Lecun discloses an image classification apparatus, comprising (Abstract; FIGS. 1-34; Page 2282, 2nd Col., Section II): one or more processors; and one or more memories coupled to the one or more processors and store programming instructions for execution by the one or more processors to (Page 2293, 1st Col., 2nd paragraph – 2nd Col., last paragraph; FIGS. 11-12): obtain an input feature map of a to-be-processed image (FIG. 2; Page 2283 2nd Col., line 19 – Page 2284, 1st Col, 1st paragraph); perform convolution processing on the input feature map based on M convolution kernels of a neural network to obtain an intermediate feature map comprising M channels, wherein M is a positive integer (FIG. 2, layers C1-S2; Page 2284, 2nd Col., Section B; Page 2313, 1st Col., Section B); perform convolution processing on the M channels of the intermediate feature map based on N matrices to obtain an output feature map comprising N channels, wherein the N matrices represent N convolution kernels, and N is a positive integer (FIG. 2, layer C3; Table 1; Page 2284, 2nd Col., Section B; Page 2313, 1st Col., Section B); and classify the to-be-processed image based on the output feature map to obtain a classification result of the to-be-processed image (FIGS. 1-2, output layer; Page 2285, 2nd Col., 2nd paragraph).
-Regarding claim 15, Lecun discloses a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores one or more programming instructions for execution by one or more processors of a device (Page 2293, 1st Col., 2nd paragraph – 2nd Col., last paragraph; FIGS. 11-12) to perform operations comprising (Abstract; FIGS. 1-34; Page 2282, 2nd Col., Section II): obtaining an input feature map of a to-be-processed image (FIG. 2; Page 2283 2nd Col., line 19 – Page 2284, 1st Col, 1st paragraph); performing convolution processing on the input feature map based on M convolution kernels of a neural network to obtain an intermediate feature map comprising M channels, wherein M is a positive integer (FIG. 2, layers C1-S2; Page 2284, 2nd Col., Section B; Page 2313, 1st Col., Section B); performing convolution processing on the M channels of the intermediate feature map based on N matrices to obtain an output feature map comprising N channels, wherein the N matrices represent N convolution kernels, and N is a positive integer (FIG. 2, layer C3; Table 1; Page 2284, 2nd Col., Section B; Page 2313, 1st Col., Section B); and classifying the to-be-processed image based on the output feature map to obtain a classification result of the to-be-processed image (FIGS. 1-2, output layer; Page 2285, 2nd Col., 2nd paragraph).
-Regarding claims 7 and 14, Lecun discloses the method of claim 1, the apparatus of claim 6, and non-transitory computer-readable storage medium of claim 15. Lecun further discloses wherein performing the convolution processing on the M channels of the intermediate feature map based on N matrices to obtain an output feature map comprising N channels, comprises: performing matrix transformation on the M channels of the intermediate feature map based on the N matrices to obtain an output feature map comprising the N channels (FIG. 2, layers S2, C3; Table 1).
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.
Claims 2-3, 5, 9-10, 12, 16-17 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Lecun et al (Proceedings of the IEEE, Vol. 86, No. 11, pp. 2278-2324, 1998), hereinafter Lecun in view of Feng et al (WO 2019041360 A1), hereinafter Feng.
-Regarding claims 2, 9 and 16, Lecun discloses the method of claim 1, the apparatus of claim 6, and non-transitory computer-readable storage medium of claim 15.
Lecun discloses wherein the quantity of channels of each of the N matrices is less than M, N is greater than M (FIG. 2, layers S2, C3; Table 1). Lecun does not disclose wherein the N matrices comprise M groups of convolution kernels, and the M groups of convolution kernels respectively correspond to the M channels of the intermediate feature map.
In the same field of endeavor, Feng teaches a pedestrian attribute recognition and positioning method and a convolutional neural network system (Abstract; FIGS. 1-10). Feng further teaches wherein the N matrices comprise M groups of convolution kernels, and the M groups of convolution kernels respectively correspond to the M channels of the intermediate feature map (Feng: FIGS. 2, 7; [0055]; [0090], “… N parallel convolutional layers … the convolutional layers may include M groups of parallel convolution kernels; The general feature of the inputted pedestrian attribute is convolved through each group of convolution kernels of the convolutional layer corresponding to each branch to obtain a new feature map …”; [0132]).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Lecun with the teaching of Feng by using M groups of convolution kernels in order to convert general features of different scales and abstraction degrees into intermediate-layer features related to achieve better recognition and positioning attributes of the object to be classified (Feng: Abstract; [0090]).
-Regarding claims 3, 10 and 17, Lecun discloses the method of claim 2, the apparatus of claim 9, and non-transitory computer-readable storage medium of claim 16.
Lecun does not disclose performing convolution on a corresponding channel of the M channels of the intermediate feature map based on each of the M groups of convolution kernels to obtain the output feature map comprising the N channels.
In the same field of endeavor, Feng teaches a pedestrian attribute recognition and positioning method and a convolutional neural network system (Abstract; FIGS. 1-10). Feng further teaches performing convolution on a corresponding channel of the M channels of the intermediate feature map based on each of the M groups of convolution kernels to obtain the output feature map comprising the N channels (Feng: FIGS. 2, 7; [0055]; [0090]; [0132]).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Lecun with the teaching of Feng by using M groups of convolution kernels in order to convert general features of different scales and abstraction degrees into intermediate-layer features related to achieve better recognition and positioning attributes of the object to be classified (Feng: Abstract; [0090]).
-Regarding claims 5, 12 and 19, Lecun discloses the method of claim 2, the apparatus of claim 9, and non-transitory computer-readable storage medium of claim 16.
Lecun does not disclose wherein a convolution kernel in each of the M groups of convolution kernels is the same as a convolution kernel in another group of the M groups of convolution kernels. In the same field of endeavor, Feng teaches a pedestrian attribute recognition and positioning method and a convolutional neural network system (Abstract; FIGS. 1-10). Feng further teaches wherein a convolution kernel in each of the M groups of convolution kernels is the same as a convolution kernel in another group of the M groups of convolution kernels (Feng: FIGS. 2, 7; [0055]; [0090]; [0132]).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Lecun with the teaching of Feng by using M groups of convolution kernels in order to convert general features of different scales and abstraction degrees into intermediate-layer features related to achieve better recognition and positioning attributes of the object to be classified (Feng: Abstract; [0090]).
Claims 6, 13 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Lecun et al (Proceedings of the IEEE, Vol. 86, No. 11, pp. 2278-2324, 1998), hereinafter Lecun in view of Dutta et al (US 20190188537 A1), hereinafter Dutta.
-Regarding claims 6, 13 and 20, Lecun discloses the method of claim 1, the apparatus of claim 8, and the storage medium of claim 15.
Lecun does not disclose performing feature splicing on the candidate output feature map and the output feature map to obtain a feature splicing feature map, wherein a quantity of channels of the feature splicing feature map is M + N.
However, above claim limitations are actually performing residual branch for transformation and skip connection for convolution processing in the neural network. Residual branch and skip connection are common practice in the field and are not inventive steps.
In the same field of endeavor, Dutta teaches utilizing building blocks for deep neural network optimized for a particular task (Dutta: Abstract; FIGS. 1-6). Dutta further teaches performing feature splicing on the candidate output feature map and the output feature map to obtain a feature splicing feature map, wherein a quantity of channels of the feature splicing feature map is M + N (Dutta: FIG. 2, residual branch 104, skip connection 108, summation element 112; [0024]).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of Lecun with the teaching of Dutta by using residual branch and skip connection in order to improve image classification performance (Dutta: [0024]).
Allowable Subject Matter
Claims 4, 11, and 18 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to XIAO LIU whose telephone number is (571)272-4539. The examiner can normally be reached Monday-Thursday and Alternate Fridays 8:30-4:30.
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, Jennifer Mehmood can be reached at (571) 272-2976. 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.
/XIAO LIU/Primary Examiner, Art Unit 2664
Prosecution Insights