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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 7/1/2026 has been entered.
Response to Amendment
This action is in response to the amendment filed on July 1st, 2026. Claims 1, 2, 11, 12, and 20 have been amended. The amended claims have been fully considered but are not persuasive. Claims 1-20 remain rejected in the application.
Response to Arguments
In response to applicant’s arguments regarding Kumari failing to disclose segmenting each reference image, the arguments are persuasive and the Examiner performed an updated prior art search and updated the office action to reflect the limitations with additional prior art. Limitations are explicitly disclosed by the new prior art (Xu: Abstract “pixel groupings ( e.g., potential segments of pixels) within each image”) (Xu: Abstract: “that most closely matches the extracted features for the associated image”)(Xu teaches dividing an image into multiple regions and compares those regions with text representing user provided category names. Further teaches determining which region corresponds to each category name).
In response to applicant’s arguments regarding Kumari failing to disclose generating noisy image features. Arguments fully considered but is not persuasive. Kumari explicitly discloses this limitation [Kumari: 0043 “In an example inference process, diffusion model 220 may receive an input text, and generate text features from the input text by encoding the text. The text features may be referred to as a "text condition." At inference. diffusion model 220 may generate an initial vector of noisy image features, then gradually denoise the vector while considering information from the text condition to synthesize a novel image corresponding to the text condition.”](teaches generating a new synthetic image at inference time using a diffusion model condition on an input text).
In response to applicant’s arguments regarding Kumari failing to disclose generating a personalized image based on features of a reference image that was NOT used during training, arguments fully considered but is not persuasive. This limitation is inherent because once the model is trained on a generic style/content database, after deployment, user picks any style/reference image from local memory. The system does not fine tune on that specific user image, it just extracts and applies them at inference to generate a style transferred image and the resulting image clearly includes features of the user’s style image because the users style image was never in the training set. Claims 1-20 remain rejected in the application.
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 1, 2, 3, 6, 11, 12, 13, 16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Kumari et al. (U.S. Patent Publication No. 2024/0185588), in view of Xu et al. (U.S. Patent Publication No. 2023/0177810).
Regarding claim 1, Kumari teaches a method for providing a personalized image using an electronic device [Kumari: 0005 “a method, apparatus, non-transitory computer readable medium, and system for fine-tuning generative models are described. One or more aspects of the method, apparatus, non-transitory computer readable medium, and system include obtaining an input text indicating an element to be included in an image”](teaches personalizing an image), the method comprising: obtaining a prompt for image generation [Kumari: 0005 “obtaining an input text”](a prompt is a text, this is explicitly the claimed limitation); extracting a keyword from the prompt [Kumari: 0005 “obtaining an input text indicating an element to be included”]; searching for one or more reference images corresponding to the keyword from among a plurality of images stored in the electronic device [Kumari: 0027 “image selection component configured to select images related to the input text”]; transmitting the prompt and the image feature information to a server [Kumari: 0033 “image generation apparatus 100 may be implemented on one or more servers connected by network 110. A server provides one or more functions to users linked by way of one or more of the various networks. In some cases, the server includes a single microprocessor board, which includes a microprocessor responsible for controlling all aspects of the server. In some cases, a server uses microprocessor and protocols to exchange data with other devices/users on one or more of the networks”][Kumari: 0035 “Network 110 facilitates the transfer of information between user 115, database 105, and image generation apparatus 110.”]; and receiving, from the server, a personalized image generated by providing the prompt and the image feature information as an input to a generative model [Kumari: 0043 “In an example inference process, diffusion model 220 may receive an input text, and generate text features from the input text by encoding the text. The text features may be referred to as a "text condition." At inference. diffusion model 220 may generate an initial vector of noisy image features, then gradually denoise the vector while considering information from the text condition to synthesize a novel image corresponding to the text condition.”](teaches generating a new synthetic image at inference time using a diffusion model condition on an input text), but fails to explicitly disclose segmenting each reference image of the one or more reference images into a plurality of regions, and selecting a region related to the keyword from among the plurality of regions; obtaining image feature information based on the region, wherein the image feature information comprises a reference embedding generated based on the region.
However, Xu discloses segmenting each reference image of the one or more reference images into a plurality of regions (interpreted as the device isolates the specific elements/part of the image (corresponding to regions) of the subject within the reference photos) (Xu: Abstract “pixel groupings ( e.g., potential segments of pixels) within each image”), and selecting a region related to the keyword from among the plurality of regions; obtaining image feature information based on the region (interpreted as computing image features from the segmented region corresponding to the keyword)(Xu: Abstract: “that most closely matches the extracted features for the associated image”)(Xu teaches dividing an image into multiple regions and compares those regions with text representing user provided category names. Further teaches determining which region corresponds to each category name), wherein the image feature information comprises a reference embedding generated based on the region (interpreted as the system creates a numerical representation or embedding from the selected image region and uses that embedding as the image feature information)[Xu: 0153 “Each segment token corresponds to an arbitrarily shaped region of the input image. The similarity is then computed between the embedding of each segment token and the text embedding of all the semantic classes present in the dataset”](teaches generating an embedding for each segmented image region).
Kumari and Xu are considered analogous to the claimed invention because they are in the same field of image processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Kumari to incorporate Xu’s teachings of segmenting regions in an image and generating embeddings for each image region. The motivation for such a combination would provide the benefit of enabling the user more personalization/control over their image.
Regarding claim 2, Kumari and Xu disclose the method of claim 1, wherein the obtaining of the image feature information comprises: obtaining a text-image pair comprising the keyword and the region corresponding to the keyword of the reference image [Kumari: 0018 “FIG. 11 shows an example of a method for selecting training data according to aspects of the present disclosure”](Kumari: 1105; Fig. 11 “Identify an image from a first training set and a caption corresponding to the image”)(teaches paired image text data in the form of an image and a corresponding caption in the training set which is text-image pair); and generating the reference embedding by converting the text-image pair into a vector representation [Kumari: 0046 “embed an input text into a vector encoding”].
Regarding claim 3, Kumari and Xu disclose the method of claim 1, wherein the generative model is deployed after being trained [Kumari: 0033 “Image generation apparatus 100 maybe implemented on a server”](teaches implementing the model on a server which is the equivalent of deploying the model), and is configured to generate the personalized image using the image feature information only during an inference operation using the generative model (interpreted as the model uses image feature information as an input at inference time only) [Kumari: 0043 “In an example inference process, diffusion model 220 may receive an input text, and generate text features from the input text by encoding the text. The text features may be referred to as a "text condition." At inference diffusion model 220 may generate an initial vector of noisy image features, then gradually denoise the vector while considering information from the text condition to synthesize a novel image corresponding to the text condition.”](teaches using the information from the text to generate a custom image corresponding to the information during the inference process), and wherein the personalized image comprises a feature of the reference image which is not used to train the generative model (interpreted as the output personalized image includes some feature of the reference image which was not used to train the generative model)(this limitation is inherent because once the model is trained on a generic style/content database, after deployment, user picks any style/reference image from local memory. The system does not fine tune on that specific user image, it just extracts and applies them at inference to generate a style transferred image and the resulting image clearly includes features of the user’s style image because the users style image was never in the training set).
Regarding claim 6, Kumari and Xu disclose the method of claim 1, further comprising applying a weight to each reference image based on a user input [Kumari: 0044 “Self-attention is a technique used in machine learning that measures the influence of all input sequence members with each other, and modifies their corresponding outputs through weights”] (teaches using weights to modify the outputted image).
Claims 11 and 20 are electronic device and non-transitory computer readable medium claims corresponding to claim 1 without any additional limitations. Thus, claims 11 and 20 are rejected for the same reasons as claim 1 above.
Claim 12 is an electronic device claim corresponding to claim 2 without any additional limitations. Thus, claim 12 is rejected for the same reasons as claim 2 above.
Claim 13 is an electronic device claim corresponding to claim 3 without any additional limitations. Thus, claim 13 is rejected for the same reasons as claim 3 above.
Claim 16 is an electronic device claim corresponding to claim 6 without any additional limitations. Thus, claim 16 is rejected for the same reasons as claim 6 above.
Claims 4 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Kumari et al. (U.S. Patent Publication No. 2024/0185588), in view of Xu et al. (U.S. Patent Publication No. 2023/0177810), in further view of Iida et al. (U.S. Patent Publication No. 2013/0066902).
Regarding claim 4, Kumari and Xu disclose the method of claim 1, but fail to explicitly disclose wherein the extracting of the keyword comprises: displaying one or more keywords extracted from the prompt; and determining the keyword for personalization from among the one or more keywords based on a user input.
However, Iida discloses wherein the extracting of the keyword comprises: displaying one or more keywords extracted from the prompt [Iida: 0041 “when content is displayed by the content display program 30, keywords are extracted from the content and the extracted keywords are displayed in the predetermined area 202, 204, or 206 in a display window of the content by the content display program 30”]; and determining the keyword for personalization from among the one or more keywords based on a user input [Iida: 0045 “Each keyword is displayed, like in the first embodiment, as a selectable button. If the button is selected, like in FIG. 5, the search result page corresponding to the keyword is displayed”][Iida: 0041 “the content and key words are displayed in the same screen and the displayed keywords naturally catch user's attention, making it easier for the user to browse related web pages by selecting keywords”](teaches that extracted keywords are displayed as selectable buttons and can be selected by the user).
Kumari, Xu, and Iida are considered analogous to the claimed invention because they are in the same field of image processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Kumari and Xu to incorporate Iida’s teachings of displaying extract keywords and allowing the user to select. The motivation for such a combination would provide the benefit of enabling the user to explicitly choose which concept in the prompt should govern personalization.
Claim 14 is an electronic device claim corresponding to claim 4 without any additional limitations. Thus, claim 14 is rejected for the same reasons as claim 4 above.
Claims 5 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Kumari et al. (U.S. Patent Publication No. 2024/0185588), in view of Xu et al. (U.S. Patent Publication No. 2023/0177810), in further view of Kale et al. (U.S. Patent Publication No. 2022/0100791).
Regarding claim 5, Kumari and Xu disclose the method of claim 1, but fails to explicitly disclose wherein the searching for the one or more reference images comprises: searching for one or more images corresponding to the keyword, and retrieving the one or more images; displaying the one or more images; and determining the one or more reference images, based on a user input.
However, Kale discloses wherein the searching for the one or more reference images comprises: searching for one or more images corresponding to the keyword [Kale: 0046 “the client device 110 can interact with digital images on the server device ( s ) 102 and / or conduct search queries for digital images on the server device ( s ) 102 and / or the network 108”], and retrieving the one or more images [Kale: 0046 “the client device can conduct a search query , receive one or more result images in response to the search query , and select one or more images from the result images”]; displaying the one or more images [Kale: 0168 “I / O interfaces 908 are configured to provide graphical data to a display for presentation to a user”]; and determining the one or more reference images, based on a user input [Kale: 0061 “the digital content contextual tagging system 106 can detect user selections of digital image search results . In particular , the digital content contextual tagging system 106 identifies selected images 406 from user selections within the interface 402”].
Kumari, Xu, and Kale are considered analogous to the claimed invention because they are in the same field of image processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Kumari and Xu to incorporate Kale’s teachings of retrieving and displaying the images. The motivation for such a combination would provide the benefit of enabling the user to visually inspect candidate images.
Claim 15 is an electronic device claim corresponding to claim 5 without any additional limitations. Thus, claim 15 is rejected for the same reasons as claim 5 above.
Claims 7 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Kumari et al. (U.S. Patent Publication No. 2024/0185588), in view of Xu et al. (U.S. Patent Publication No. 2023/0177810), in further view of Shlens et al. (EP 3 526 770).
Regarding claim 7, Kumari and Xu disclose the method of claim 1, but fails to explicitly disclose further comprising: storing the image feature information; and visualizing and displaying the stored image feature information in response to another request to generate a new personalized image after the image feature information is stored.
However, Shlens discloses further comprising: storing the image feature information [Shlens: 0016 “the subsystem 110 maintains data specifying respective parameter values for each image style in a set of image styles 116”](teaches storing image information); and visualizing and displaying the stored image feature information in response to another request to generate a new personalized image after the image feature information is stored (interpreted as when the user later initiates another request for a new personalized image, the system uses the previously stored feature information and visualizes/displays it)[Shlens: 0073 “displaying data to and receiving user input from a user”](teaches displaying the data while receiving input from the user).
Kumari, Xu, and Shlens are considered analogous to the claimed invention because they are in the same field of image processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Kumari and Xu to incorporate Shlen’s teachings of displaying data in response to a user’s input. The motivation for such a combination would provide the benefit of providing users with additional controls.
Claim 17 is an electronic device claim corresponding to claim 7 without any additional limitations. Thus, claim 17 is rejected for the same reasons as claim 7 above.
Claims 8, 9, 18, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Kumari et al. (U.S. Patent Publication No. 2024/0185588), in view of Xu et al. (U.S. Patent Publication No. 2023/0177810), in further view of Benzarti et al. (U.S. Patent Publication No. 2012/0219191).
Regarding claim 8, Kumari and Xu disclose the method of claim 1, but fail to explicitly disclose further comprising: extracting a text description about each reference image from each reference image; and changing the prompt based on the text description.
However, Benzarti discloses further comprising: extracting a text description about each reference image from each reference image [Benzarti: 0006 “Another tool provided by many electronic social networks is item tagging. In this approach, a user who uploads an item can tag the item with one or more textual descriptors. The tags are thus metadata associated with the item”]; and changing the prompt based on the text description [Benzarti: 0021 “the role of the tag recommendation system 10 is to provide search recommendations”](teaches the tag (description) influences the search which corresponds to prompt).
Kumari, Xu, and Benzarti are considered analogous to the claimed invention because they are in the same field of image processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Kumari and Xu to incorporate Benzarti’s teachings of utilizing item tags. The motivation for such a combination would provide the benefit of providing users with additional personalization.
Regarding claim 9, Kumari, Xu, and Benzarti disclose the method of claim 8, wherein the obtaining of the image feature information comprises obtaining the image feature information comprising the text description of the reference image [Kumari: 0112 “experimental data indicates forgetting of concepts is maximized when finetuning for new concepts with text description similar to the target image”][Kumari: 0042 “diffusion model 220 encodes the training image to obtain image features.”].
Claim 18 is an electronic device claim corresponding to claim 8 without any additional limitations. Thus, claim 18 is rejected for the same reasons as claim 8 above.
Claim 19 is an electronic device claim corresponding to claim 9 without any additional limitations. Thus, claim 19 is rejected for the same reasons as claim 9 above.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Kumari et al. (U.S. Patent Publication No. 2024/0185588), in view of Xu et al. (U.S. Patent Publication No. 2023/0177810), in further view of Rothschild (U.S. Patent No. 10,108,836).
Regarding claim 10, Kumari and Xu disclose the method of claim 1, but fail to explicitly disclose further comprising: detecting one or more products included in the personalized image; and displaying information related to the one or more products.
However, Rothschild discloses further comprising: detecting one or more products included in the personalized image (Rothschild: Col. 1, Lines, 59-60 “The system also includes a product identifier to identify the product based on the recognized logo”); and displaying information related to the one or more products (Rothschild: Col. 4, Line 3 “product data may then be displayed to the user via a display”).
Kumari, Xu, and Rothschild are considered analogous to the claimed invention because they are in the same field of image processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Kumari and Xu to incorporate Rothschild’s teachings of detecting and displaying products. The motivation for such a combination would provide the benefit of enabling users to obtain product details.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AHMED TAHA whose telephone number is (571)272-6805. The examiner can normally be reached 8:30 am - 5 pm, Mon - Fri.
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, XIAO WU can be reached at (571)272-7761. 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.
/AHMED TAHA/Examiner, Art Unit 2613
/XIAO M WU/Supervisory Patent Examiner, Art Unit 2613
Prosecution Insights