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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 07/1/2024 and 3/19/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Arguments
Claims 1-2, 4-10, 13-14, 16, and 18-21 have been amended. Claims 1-11, 13-14, and 16-22 are now being considered. Applicant’s arguments, filed 7/7/2026, with respect to the rejection(s) of claim(s) 1-2, 4-10, 13-14, 16, and 18-21 under 35 U.S.C 102 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Nakamura (United .
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.
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.
Claim(s) 1-11, 13-14, and 16-22 is/are rejected under 35 U.S.C. 103 as being unpatentable over Mitra et. al. (United States Patent Application Publication US 2022/0028139 A1) in view of Nakamura (United States Patent Application Publication US 2023/0067730 A1).
Regarding claim 1, Mitra et. al. discloses an image processing method, comprising: acquiring data to be processed, wherein the data to be processed comprises Gaussian noise or an image to be converted (Mitra et. al., [0095]); and processing the data to be processed by a facial attribute determination model to obtain a facial image corresponding to the data to be processed, wherein at least one target feature in the target facial image is matched with corresponding at least one preset facial feature (Mitra et. al., [0093]-[0094], the main attributes include gender, pitch, yaw, eyeglasses, age, facial hair, expression, and baldness).
However, Mitra et. al. fails to disclose wherein the facial attribute determination model is obtained by training the facial attribute determination model using at least one training sample, and wherein the training comprises: inputting the at least one training sample to the facial attribute determination model to obtain feature vectors; generating a first image without an attribute feature based on the feature vectors; generating a second image with an attribute feature based on the feature vectors; determining attribute information and facial matching information based on the first image and the second image; and updating parameters of the facial attribute determination model based on a loss function computed based on the attribute information and the facial matching information.
Nakamura teaches wherein the facial attribute determination model is obtained by training the facial attribute determination model using at least one training sample, and wherein the training comprises: inputting the at least one training sample to the facial attribute determination model to obtain feature vectors; generating a first image without an attribute feature based on the feature vectors; generating a second image with an attribute feature based on the feature vectors; determining attribute information and facial matching information based on the first image and the second image; and updating parameters of the facial attribute determination model based on a loss function computed based on the attribute information and the facial matching information (Nakamura Figure 2, 4, 16, 17, [0004], [0038]-[0043], [0045], [0046]: a vector generation unit generates an image feature vector representing features of an image. As a specific method for generating an image feature vector, a convolutional neural network (CNN), which is a type of neural network, is used. [0048]: A first feature group obtaining unit obtains image feature vectors generated from facial images included in a first group of a Pseudo set obtained by the training set obtaining unit. A second vector group obtaining unit obtains image feature vectors generated from facial images included in a second group of a Pseudo set obtained by the training set obtaining unit. [0055]-[0059]: A generation parameter updating unit updates parameters for generating an image feature vector. Specifically, updating is performed so as to reduce a distance between image feature vectors representing features of facial images of the same person (same category). Parameters are updated using a loss function shown in Equations 5 and 6.
PNG
media_image1.png
905
428
media_image1.png
Greyscale
PNG
media_image2.png
918
670
media_image2.png
Greyscale
These features are important to the claimed invention because the training set generates the facial images based on the attributes selected and similarities found. Noise is removed between renderings via the loss function to improve the accuracy of the neural network model. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have combined the teachings of Mitra et.al. and Nakamura so that all of these features are included in the solution of the claimed invention.
Regarding claim 13, which is an electronic device claim, comprising: at least one processor; and a storage apparatus, configured to store at least one program, wherein the at least one program, when executed by the at least one processor, causes the electronic device to: acquire data to be processed, corresponds to the image processing method claim 1 and thus, the rejection rationale for claim 1 is incorporated herein.
Regarding claim 14, which is a non-transitory storage medium claim comprising computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, cause the computer processor to: acquire data to be processed, corresponds to the electronic device claim 13 of which the rejection analysis is incorporated herein.
Regarding claim 2, Mitra et. al. further discloses the method according to claim 1, wherein processing the data to be processed by the facial attribute determination model to obtain the facial image corresponding to the data to be processed comprises: determining a feature vector to be concatenated corresponding to the data to be processed; concatenating the feature vector to be concatenated with a preset feature vector corresponding to the at least one preset facial feature, to obtain a feature vector corresponding to the facial image; and processing the feature vector to obtain the facial image (Mitra et. al. Figure 12, [0006], a modified feature vector is computed based on the latent vector using the mapping network, wherein the mapping network comprises a non-linear dependency on the target attribute values and the preserved attribute values, and generate a modified image based on the modified feature vector, wherein the modified image includes the target attributes and the remaining subset of the original attributes).
Regarding claim 16, which is the electronic device according to claim 13, which corresponds to the method of claim 2 which the rejection analysis is incorporated herein.
Regarding claim 3, Mitra et. al. further discloses the method according to claim 2, wherein determining a feature vector to be concatenated corresponding to the data to be processed comprises: determining a feature vector to be concatenated corresponding to the Gaussian noise based on a first feature extraction module (Mitra et. al., [0093]-[0095], first sample 10k samples from the Gaussian Z space of the StyleGAN1 of StyleGAN2), based on a determination that the data to be processed is the Gaussian noise; and determining a feature vector to be concatenated corresponding to the image to be converted based on a second feature extraction module, based on a determination that the data to be processed is the image to be converted (Mitra et. al. [0144]-[0145], Image2StyleGAN, InterfaceGAN, and multiple edits are performed simultaneously).
Regarding claim 17, which is the electronic device according to claim 16, which corresponds to the method claim 3 which the rejection analysis is incorporated herein.
Regarding claim 4, Mitra et. al. further discloses the method according to claim 1, wherein after obtaining the facial image corresponding to the data to be processed, the method further comprises: determining at least one attribute corresponding to the facial image based on a pre-trained attribute classifier, to correct at least one of the parameters of the facial attribute determination model based on the at least one attribute, wherein the at least one attribute is matched with an attribute identifier of the at least one preset facial feature (Mitra et. al. Figure 5, 6, 10, [0005] a modified image includes the change to the target attribute and retains the at least one preserved attribute from the original image).
Regarding claim 18, which is the electronic device according to claim 13, which corresponds to the method claim 4 which the rejection analysis is incorporated herein.
Regarding claim 5, Mitra et. al. further discloses the method according to claim 1, further comprising: pruning the facial attribute determination model (Mitra et. al. Figure 7, training of a CNN network for generating realistic images of faces, [0024]).
Regarding claim 19, which is the electronic device according to claim 13, which corresponds to the method claim 5 which the rejection analysis is incorporated herein.
Regarding claim 6, Mitra et. al. further discloses the method according to claim 5, further comprising, before training the facial attribute determination model: constructing the facial attribute determination model, based on an attribute editing sub-model to be trained, a pre-trained adversarial model, a pre-trained attribute classification model, and a pre-trained facial matching model, wherein the attribute classification model is configured to determine a facial feature of an image output by the adversarial model, and the facial matching model is configured to determine a matching degree of a facial image output based on the adversarial model, and the adversarial model is configured to output two facial images, wherein one of the facial images is matched with a preset facial feature set in the attribute editing sub-model to be trained (Mitra et. al. Figure 1, 4, 7, [0032] complex attributes of an original image are modified while preserving other attributes, including attributes representing the identity of a person in the image. Changes of the image can include orientation of the original image, modified lighting, facial expression, modified gender, and age, [0038] image editing application receives input from a user indicating the image to be edited, along with a target attribute value to be changed).
Regarding claim 20, which is the electronic device according to claim 19, which corresponds to the method claim 6 which the rejection analysis is incorporated herein.
Regarding claim 7, Mitra et. al. further discloses the method according to claim 6, wherein the adversarial model comprises: a feature preprocessing sub-model and an image generation sub-model; the feature preprocessing sub-model comprises a first feature extraction module; the image generation sub-model comprises a first image generation submodule and a second image generation submodule; and the feature preprocessing sub-model further comprises a second feature extraction module (Figure 11, edit-specific subset selection, CNN model, Figure 4 attribute selection by user, [0032]-[0033] multiple target attributes are changed sequentially, Figure 5 shows a method of editing an image).
Regarding claim 21, which is the electronic device according to claim 20, which corresponds to the method claim 7 which the rejection analysis is incorporated herein.
Regarding claim 8, Mitra et. al. further discloses the method according to claim 7, wherein constructing the facial attribute determination model comprises: determining an output result of the first feature extraction module or the second feature extraction module as an input of the attribute editing sub-model to be trained and the first image generation submodule, determining an output of the attribute editing sub-model to be trained as an input of the second image generation submodule, and determining an output of the first image generation submodule and an output of the second image generation submodule as inputs of the attribute classification model and the facial matching model, to construct the facial attribute determination model (Mitra et. al. Figure 11).
Regarding claim 11, Mitra et. al. further discloses the method according to claim 1, wherein the preset facial features comprise at least one of following: a facial feature about wearing at least one type of accessories, facial features of different age stages, facial features of different angles, facial features of different hairstyles, facial features of different hair color combinations, and facial features of different facial expressions (Mitra et. al. Figure 4).
Regarding claim 22, which is the electronic device according to claim 13, which corresponds to the method claim 11 which the rejection analysis is incorporated herein.
Regarding claim 9, Mitra et. al. further discloses the method according to claim 7, wherein training the facial attribute determination model comprises: obtaining a plurality of training samples the at least one training sample; inputting, for the plurality of training samples, the data to be trained in the current training sample to the first feature extraction module or the second feature extraction module to obtain a first feature vector corresponding to the current training sample; concatenating the first feature vector with an attribute feature vector corresponding to at least one preset facial feature based on the attribute editing sub-model to be trained to obtain a first attribute feature vector; inputting the first feature vector to the first image generation submodule to obtain an image without an attribute feature, and inputting the first attribute feature vector to the second image generation submodule to obtain an image with an attribute feature; inputting the image with an attribute feature and the image without an attribute feature to the attribute classification model to obtain attribute information to be compared, and inputting the image with an attribute feature and the image without attribute features to the facial matching model to obtain facial matching information (Mitra et. al. Figures 4-7, neural network system for editing original image based on facial feature attributes); processing the attribute information to be compared, the facial matching information, and the preset facial feature in the attribute editing sub-model to be trained based on a loss function in the attribute editing sub-model to be trained to obtain a loss value; and correcting a model parameter in the attribute editing sub-model to be trained based on the loss value, determining a convergence of the loss function as a training target, and obtaining a facial attribute determination model to be used through training (Mitra et. al. [0095], Gaussian loss function in the form of the Gaussian probability density function, along with the algorithm for the concatenation operation of the neural network).
Regarding claim 10, Mitra et. al. further discloses the method according to claim 9, wherein pruning the facial attribute determination model comprises: removing the attribute classification model, the facial matching model, and the first image generation sub-model, to obtain the target facial attribute determination model (Mitra et. al. Figure 10, compute a latent vector based on the original feature vector and the original attribute values, which captures the essential features and discards redundant information).
Conclusion
Response to Amendment
Examiner has carefully considered the amendments to the claims and performed an updated search. New prior art has been found to rejection all amended claims.
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 JESSICA YIFANG LIN whose telephone number is (571)272-6435. The examiner can normally be reached M-F 7:00am-6:15pm, with optional day off.
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, Vu Le can be reached at 571-272-7332. 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.
/JESSICA YIFANG LIN/Examiner, Art Unit 2668 August 19, 2026
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights