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 .
Response to Amendment
Applicant’s amendments received 8/22/2025 in response to the Non-Final Rejection mailed 5/29/2025 has been made of record. Claims 1-20 remain pending, and claim 21 has newly been added.
Response to Arguments
Applicant’s amendments and arguments with respect to the rejections of claims 1-20 under 35 U.S.C. 101 have been fully considered and are persuasive, specifically wherein the full-frame image is processed using global attention used for removing shadows detected in the image. Therefore, the rejection has been withdrawn.
Applicant’s amendments and arguments with respect to the rejections of claims 3, 11, and 13 under 35 U.S.C. 112 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn.
Applicant’s arguments with respect to the amended claims have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Upon further consideration, a new ground of rejection is made in view of Lin in view of Hao, and together does meet each limitation of the amended claims.
Based on these facts, this action is made FINAL.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 9/12/2025 and 12/16/2025 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, 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.
sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-2, 9-10, 15-16, and 21 are rejected under 35 U.S.C. 103 as being anticipated by Lin (Yun-Hsuan Lin et al. “BEDSR-Net: A Deep Shadow Removal Network from a Single Document Image”. 2020 June 19) in view of Hao (CN-114187186-A).
Regarding claim 1, Lin discloses an electronic device determining a global attention map (Lin Fig. 2, embodied within the background estimation network), wherein the electronic device comprises:
a hardware accelerator, configured to process at least one tile of a full-frame image (Lin Page 3/10 and Fig. 2, embodied within the background estimation network to process removal of a shadow in the image);
a memory configured to store instructions (Lin Page 3/10 and Fig. 2, embodied within the background estimation network to train the network); and
at least one processor, communicatively coupled to the hardware accelerator and the memory, wherein the instructions when executed by the one or more processors individually or collectively, cause the electronic device (Lin Page 3/10 and Fig. 2, embodied within the background estimation network to train the network) to:
subsample the full-frame image to obtain a subsampled image (Lin 3/10-4/10 and Fig. 2, sample the shadow image to obtain the background color),
determine the global attention map based on the subsampled image (Lin 3/10-4/10 and Fig. 2, determine the attention map based on the predicated background color),
obtain, by the hardware accelerator, feature information of the full-frame image by processing the at least one tile of the full-frame image based on the global attention map (Lin 3/10-5/10 and Fig. 2, obtain the shadow mask of the image based on the attention map), and
wherein the global attention map is performed using the subsampled full- frame image (Lin 3/10-4/10 and Fig. 2, the attention map is based using the predicated background color).
Lin does not disclose where Hao teaches process the full-frame image using global attention resulting in a first rectified image, wherein the global attention map is used for removing a shadow detected in the full-frame image (Hao, 7/24, generate the image using the attention map to obtain a shadow-free image).
It would have been obvious, before the effective date of the claimed invention, to one of ordinary skill in the art, to modify the configuration of the hardware accelerator of Lin with the teachings of Hao to include removing shadows in a fill-frame image in order to improve the image visual quality and readability.
Regarding claim 2, Lin discloses the electronic device of claim 1, wherein the determining of the global attention map based on the subsampled image, comprises:
extracting local edge features from the subsampled image (Lin 5/10 and Fig. 3, extract shadow masks including around edges);
generating one or more branches of the local edge features (Lin 5/10 and Fig. 3, generate the shadow mask locations of the image);
reshaping on the one or more branches of the local edge features (Lin 5/10 and Fig. 3, shaping the mask to remove the shadow within the image); and
determining the global attention map based on the reshaped local edge features (Lin 3/10-4/10 and Fig. 2, determine the attention map for determining how likely each pixel belongs in the shadow-free background).
Regarding claim 21, Lin discloses the electronic device of claim 1, wherein the determination of the global attention map is performed by providing the subsampled image to a deep learning model (Lin 4/10, use a deep network to predict background color).
Regarding claims 9-10 and 15-16, the rationale provided in the rejection of claims 1-2 is incorporated herein. In addition, the electronic device of claims 1-2 corresponds to the method of claims 9-10 and the computer readable medium of claims 15-16, and performs the steps disclosed herein.
Claims 3-8, 11-14, and 17-20 are rejected under 35 U.S.C. 103 as being unpatentable over Lin in view of Hao, and further in view of Cheng (Qishang Cheng et al. “Learn to Pay Attention Via Switchable Attention for Image Recognition” 2020 August 08).
Regarding claim 3, the combination of Lin and Hap together does not disclose where Cheng teaches the electronic device of claim 1, wherein the hardware accelerator is further configured to:
obtain a local attention map of the full-frame image (Cheng Page 2/6-3/6 and Fig. 2, the input image includes operation of the local spatial attention);
determine core features of the full-frame image based on the local attention map, the global attention map, and at least one tile of the full-frame image (Cheng Page 2/6-3/6 and Fig. 2, determine parameters of the input image that includes operation of the local spatial attention, the global spatial attention, and vector of the input image); and
obtain the feature information of the full-frame image including the core features (Cheng Page 2/6-3/6 and Fig. 2, determine the image classification based on the input image based on the associated parameters).
It would have been obvious, before the effective date of the claimed invention, to one of ordinary skill in the art, to modify the configuration of the hardware accelerator of Lin and Hao with the teachings of Cheng to include obtaining and determining information in order to further enhance the image and render optimal performance.
Regarding claim 4, the combination of Lin, Hao, and Cheng together discloses the electronic device of claim 1, wherein the electronic device further comprises at least one of: a parallel switch, configured to bypass a connection of the global attention map with the hardware accelerator; or a series switch, configured to gate the connection of the global attention map with the hardware accelerator (Cheng Page 2/6-3/6 and Fig. 2, connect the global spatial attention to be used when needed with the input image).
Regarding claim 5, the combination of Lin, Hao and Cheng together discloses the electronic device of claim 4, wherein the series switch is configured to: allow a flow of the global attention map in case that the global attention map is required, and block the flow of the global attention map in case that the global attention map is not required (Cheng Page 2/6-3/6 and Fig. 2, switch to the global spatial attention to be used when required, bypass to another when not needed).
Regarding claim 6, the combination of Lin, Hao, and Cheng together discloses the electronic device of claim 4, wherein the parallel switch is configured to: block a residual bypass in case that the global attention map is required, and allow the residual bypass in case that the global attention map is not required (this situation does not take place since the parallel switch was not selected as disclosed in claim 4; instead the series switch was disclosed and detailed above in claims 4-5).
Regarding claim 7, the combination of Lin, Hao, and Cheng together discloses the electronic device of claim 4, wherein at least one of the parallel switch and the series switch comprises convolutions of 1x1 kernel size with non-trainable weights (Cheng Page 2/6-3/6 and Fig. 2, the convolution kernel is 1x1).
Regarding claim 8, the combination of Lin, Hao, and Cheng together discloses the electronic device of claim 1, wherein the subsampled image is obtained based on at least one of down sampling kernels or learned downsizing kernels (Cheng Page 2/6-3/6 and Fig. 2, the data includes kernels that is down sampled to 1x1).
Regarding claims 11-14 and 17-20, the rationale provided in the rejection of claims 3, 5, and 8 is incorporated herein. In addition, the electronic device of claims 3, 5, and 8 corresponds to the method of claims 11-14 (additionally, within claim 13, Lin discloses the global information of the full-frame image includes low-light information, Lin 3/10-4/10 and Fig. 2, determine the attention map determines how likely each pixel belongs in the shadow-free background from the shadow image) and the computer readable medium of claims 17-20, and performs the steps disclosed herein.
Conclusion
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 Vincent Rudolph whose telephone number is (571)272-8243. The examiner can normally be reached M-F 7:30 AM - 3:30 PM.
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.
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.
/VINCENT RUDOLPH/ Supervisory Patent Examiner, Art Unit 2671
Prosecution Insights