DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . 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 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.
Information Disclosure Statement
2. The information disclosure statements (IDS) submitted on the following dates are in compliance with the provisions of 37 CFR 1.97 and are being considered by the Examiner: 07/11/2024; 07/08/2025.
Claim Rejections - 35 USC § 103
3. 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
4. Claims 1-6 are rejected under 35 U.S.C. 103 as being unpatentable over Phogat et al., (“Phogat”) [US-2025/0078341-A1] in view of Chan et al., (“Chan”) [US-2025/0278437-A1]
Regarding claim 1, Phogat discloses a data processing system for automatically recoloring a digital artifact (Phogat- ¶0002, at least discloses systems, methods, and non-transitory computer-readable media that recolor a digital design based on a color theme from a digital image. More particularly, in one or more implementations, the systems recolor a digital design based on a color theme from a digital image generated utilizing a text-to-image diffusion model), the data processing system comprising:
a processor (Phogat- ¶0125, at least discloses one or more processors); and
a memory in communication with the processor, the memory comprising executable instructions that, when executed by the processor alone or in combination with other processors, cause the data processing system to perform functions (Phogat- ¶0125, at least discloses one or more processors and system memory […] physical and other computer-readable media for carrying or storing computer-executable instructions and/or data structures. In particular, one or more of the processes described herein may be implemented at least in part as instructions embodied in a non-transitory computer-readable medium and executable by one or more computing devices (e.g., any of the media content access devices described herein). In general, a processor (e.g., a microprocessor) receives instructions, from a non-transitory computer-readable medium, (e.g., a memory), and executes those instructions, thereby performing one or more processes, including one or more of the processes) of:
receiving the digital artifact and one or more input images (Phogat- ¶0002, at least discloses system receives an indication of a selection of a digital design [digital artifact] and a text prompt input; Fig. 2 and ¶0037-0038, at least disclose FIG. 2 shows the design recolor system 102 receiving a digital image 202 (e.g., PNG or a JPEG) [one or more input images] generated from a text prompt 204 […] the digital image 202 includes an image designated as a source for transferring colors. Specifically, the design recolor system 102 obtains the digital image 202 by utilizing a text-to-image diffusion neural network and transfers colors from the digital image 202 to a digital design 200 (e.g., a SVG) [digital artifact]; Fig. 7 and ¶0097, at least disclose the design recolor system 102 receiving an indication of a selection within a graphical user interface of a digital design 700 [digital artifact] from a client device);
from a user interface screen of an application being executed on a user client device (Phogat- ¶0095, at least discloses the text vector representation (e.g., the text query) to generate text-conditioned images; Fig. 7 and ¶0097, at least disclose the design recolor system 102 receiving an indication of a selection within a graphical user interface of a digital design 700 from a client device [user interface screen of an application]; ¶0107, at least discloses the client device application manager 814 manages the graphical user interface for a user/designer of a client device to provide a text prompt input or for indicating the selection of a digital design (e.g., a target design)), to create a design that includes the digital artifact and the one or more input images (Phogat- ¶0002, at least discloses system receives an indication of a selection of a digital design [digital artifact] and a text prompt input; Fig. 2 and ¶0037-0038, at least disclose FIG. 2 shows the design recolor system 102 receiving a digital image 202 (e.g., PNG or a JPEG) [one or more input images] generated from a text prompt 204 […] the digital image 202 includes an image designated as a source for transferring colors. Specifically, the design recolor system 102 obtains the digital image 202 by utilizing a text-to-image diffusion neural network and transfers colors from the digital image 202 to a digital design 200 (e.g., a SVG) [digital artifact]; Fig. 7 and ¶0097, at least disclose the design recolor system 102 receiving an indication of a selection within a graphical user interface of a digital design 700 [digital artifact] from a client device);
constructing a prompt, via a prompt construction engine, for transmission to a generative artificial intelligence (Al) tool, the prompt requesting the generative AI tool to identify a plurality of colors (Phogat- ¶0024, at least discloses receiving, via input from a client device, a text prompt [prompt] and generating a digital image from the text prompt utilizing a text-to-image diffusion model […] the design recolor system receives a text prompt from a designer indicating specific color schemes/themes and the design recolor system generates the digital image according to the indications of the text prompt; Fig. 1 and ¶0032, at least disclose The client device 110 includes one or more applications (e.g., an image generation application) for processing text prompts and recoloring digital designs or digital images in accordance with the media management system 104 […] the client application 112 works in tandem with the design recolor system 102 to process text prompts utilizing a text-to-image diffusion neural network 103 to generate text-conditioned images; ¶0035, at least discloses the design recolor system 102 on the client device 110 receives a text prompt that includes an indication of colors. The client device 110 transmits the text prompt [prompt for transmission to a generative artificial intelligence (Al) tool] with the multiple concepts to the server(s) 106. In response, the design recolor system 102 on the server(s) 106 utilizes a diffusion neural network to generate a text-conditioned image [prompt requesting the generative AI tool to identify a plurality of colors]; ¶0037, at least discloses the design recolor system 102 processes the text prompt 204 that describes or indicates one or more colors (e.g., color features, color schemes, or color themes); ¶0095, at least discloses the text vector representation (e.g., the text query) to generate text-conditioned images; Fig. 7 and ¶0101, at least disclose the digital image manager 802 receives a text prompt from a designer of a client device and passes the text prompt to the text-to-image diffusion model manager 812 which then passes a digital image back to the digital image manager 802; ¶0106, at least discloses The text-to-image diffusion model manager 812 receives text prompts from the digital image manager 802 [prompt construction engine]. In particular, the text-to-image diffusion model manager 812 generates a digital image from a text prompt utilizing various denoising neural networks conditioned on the text prompt. Furthermore, the text-to-image diffusion model manager 812 [generative AI tool] pre-trains a diffusion neural network for generating text-conditioned images);
transmitting the prompt to the generative AI tool (Phogat- Fig. 7 and ¶0101, at least disclose the digital image manager 802 receives a text prompt from a designer of a client device and passes the text prompt to the text-to-image diffusion model manager 812 which then passes a digital image back to the digital image manager 802 [transmitting the prompt to the generative AI tool]);
receiving from the generative AI tool the plurality of colors (Phogat- ¶0020, at least discloses digital designs contain thousands of colors and the design recolor system utilizes quantization to reduce the range of colors to a smaller range (e.g., reduce the color palette size) […] quantization of the pixel values helps colors within the digital design maintain their relationship; ¶0038, at least discloses the design recolor system 102 obtains the digital image 202 by utilizing a text-to-image diffusion neural network [generative AI tool] and transfers colors from the digital image 202 to a digital design 200 (e.g., a SVG); ¶0043, at least discloses the design recolor system 102 assigns colors of the digital design 200 to the set of color clusters which maintains color relationships within the digital design 200 and reduces the color palette size (e.g., the range) of the digital design 200; Fig. 7 and ¶0098, at least disclose the design recolor system 102 transfers colors from the digital image 706 to the digital design 700 to generate a recolored digital design 708 […] FIG. 7 shows the digital design 700 with warm colors (reds and oranges) and the digital image 706 with cool colors (blues, and blacks) and the recolored digital design 708 conforms with the cool colors shown in the digital image 706.);
recoloring the digital artifact based on the base color palette (Phogat- ¶0020, at least discloses digital designs contain thousands of colors and the design recolor system utilizes quantization to reduce the range of colors to a smaller range (e.g., reduce the color palette size) […] quantization improves the effectiveness of a color affine transformation (e.g., because the range of colors is reduced and color quantization results in an efficient representation of colors in an image/design); Fig. 7 and ¶0098, at least disclose the design recolor system 102 transfers colors from the digital image 706 to the digital design 700 to generate a recolored digital design 708. In particular, the design recolor system 102 utilizes a color affine transformation algorithm that recolors the digital design 700 according to the colors of the digital image 706).
Phogat does not explicitly disclose receiving a user query; and transmitting the plurality of colors to a base palette generation engine, the base palette generation engine generating a base color palette based on at least one of one or more colors of the one or more input images and the plurality of colors received from the generative AI tool.
However, Chan discloses
receiving a user query (Chan- Fig. 10 and ¶0062-0064, at least disclose the asset recommendation module 206 include a SQL conversion module 1002 to convert a text-based input 122 or other input into a SQL query. A text-based input 122 of “The Team1 vs Team2 finals in 2003 was particular exciting” is converted to: SELECT * FROM df WHERE team_name=“TEAM1” AND opponent=“TEAM2” AND season=‘2002-03’ AND period=2 AND playoffs=1 ORDER BY date LIMIT 10. The SQL query 1004 is used by a search module 1006 to search to the asset data 214 (i.e., the dataset) to generate filtered data 1008 by a machine-learning model 1010, e.g., by a table generation module 1012 as a table 1014);
transmitting the plurality of colors to a base palette generation engine, the base palette generation engine generating a base color palette based on at least one of one or more colors of the one or more input images and the plurality of colors received from the generative AI tool (Chan- Fig. 12 and ¶0067, at least disclose generating a color palette 224 as part of the asset recommendation data 208. To generate the color palette 224 in this example, a digital image generation module 1202 employs a machine-learning model 1204 to generate digital images 1206 based on the text-based input 122, using generative artificial intelligence. A color palette extraction module 1208 [base palette generation engine] is then leveraged to extract the color palette 224, e.g., by computing color histograms (e.g., using five bins), from the digital images 1206. Each color histogram becomes a color palette 224 with color sorted by luminosity in one or more examples; ¶0072, at least discloses a color palette and visual interaction 1302 is supported that causes recoloring of a visualization based on the color palette. Once a desired color palette is selected from a list of asset recommendations, for instance, a user input is received by the asset interaction module 226 to select a visualization, e.g., SVG, GIF, or other visualization. In response, the asset interaction module 226 maps the color palette onto colors of that asset. Given two histograms, e.g., one from the graphic and one from the color palette, colors are transferred via mapping to minimize an “Earth Mover Distance.” Therefore, the resulting colors preserve properties of the visualization such as categorical properties, diverging properties, line color schemes, and the like.).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat to incorporate the teachings of Chan, and apply receiving a user query and generating the color palette into Phogat’s teachings for receiving a user query, from a user interface screen of an application being executed on a user client device, to create a design that includes the digital artifact and the one or more input images; constructing a prompt, via a prompt construction engine, for transmission to a generative artificial intelligence (Al) tool, the prompt requesting the generative AI tool to identify a plurality of colors based on the user query; and transmitting the plurality of colors to a base palette generation engine, the base palette generation engine generating a base color palette based on at least one of one or more colors of the one or more input images and the plurality of colors received from the generative AI tool.
Doing so would provide large language models provides a foundational tool in artificial intelligence for understanding and generating human language, powering a wide range of applications from conversational agents to content creation tools.
Chan further discloses
receiving the digital artifact and one or more input images (Chan- Fig. 5 and ¶0055, at least disclose a user interface 128 including an input panel 502 configured for output of representations of a plurality of assets (block 1406). The representations, for instance, are depicted in a visualization menu 504 as visualizations of a “canary” [digital artifact] and “bird” [one or more input images] that are generated based on the text-based input 122. The representations are selectable from the visualization menu 504 for inclusion in a canvas panel 506 (block 1408));
recoloring the digital artifact based on the base color palette (Chan- ¶0072, at least discloses a color palette and visual interaction 1302 is supported that causes recoloring of a visualization based on the color palette.)
Regarding claim 2, Phogat in view of Chan, discloses the data processing system of claim 1, and further discloses wherein the generative AI tool is a large language model (Chan- ¶0003, at least discloses A text-based input is received and asset recommendation data is generated based on the text-based input using a machine-learning model, e.g., a large language model (LLM)).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat to incorporate the teachings of Chan, and apply the large language model (LLM) into Phogat’s teachings in order the generative AI tool is a large language model.
The same motivation that was utilized in the rejection of claim 1 applies equally to this claim.
Regarding claim 3, Phogat in view of Chan, discloses the data processing system of claim 1, and further discloses wherein:
the generative AI tool is a multimodal model (Chan- ¶0054, at least discloses A family of generative machine-learning models are then employed by the machine-learning model 210 of the asset recommendation module 206 to generate the different asset types […] “GPT-3.5” is usable for text completion, further discussion of which may be found at “OpenAI. 2023, https://platform.openai.com/docs/models/gpt-3-5.” [Wingdings font/0xE0] suggests a multimodal model),
the prompt to the generative AI tool includes the user query and the one or more images (Phogat- ¶0024, at least discloses receiving, via input from a client device, a text prompt [prompt] and generating a digital image from the text prompt utilizing a text-to-image diffusion model […] the design recolor system receives a text prompt from a designer indicating specific color schemes/themes and the design recolor system generates the digital image according to the indications of the text prompt; Fig. 1 and ¶0032, at least disclose The client device 110 includes one or more applications (e.g., an image generation application) for processing text prompts and recoloring digital designs or digital images in accordance with the media management system 104 […] the client application 112 works in tandem with the design recolor system 102 to process text prompts utilizing a text-to-image diffusion neural network 103 to generate text-conditioned images; Chan- Fig. 5 and ¶0055, at least disclose a user interface 128 including an input panel 502 configured for output of representations of a plurality of assets (block 1406). The representations, for instance, are depicted in a visualization menu 504 as visualizations of a “canary” and “bird” [one or more input images] that are generated based on the text-based input 122; Fig. 10 and ¶0062-0064, at least disclose the asset recommendation module 206 include a SQL conversion module 1002 to convert a text-based input 122 or other input into a SQL query. A text-based input 122 of “The Team1 vs Team2 finals in 2003 was particular exciting” is converted to: SELECT * FROM df WHERE team_name=“TEAM1” AND opponent=“TEAM2” AND season=‘2002-03’ AND period=2 AND playoffs=1 ORDER BY date LIMIT 10. The SQL query 1004 is used by a search module 1006 to search to the asset data 214 (i.e., the dataset) to generate filtered data 1008 by a machine-learning model 1010, e.g., by a table generation module 1012 as a table 1014), and
the generative AI tool identifies the plurality of colors (see Claim 1 rejection for detailed analysis) based on the user query and colors of the one or more images (Chan- Fig. 5 shows visualizations of a “canary” and “bird” [one or more input images] that are generated based on the text-based input 122; Fig. 10 and ¶0062-0064, at least disclose the asset recommendation module 206 include a SQL conversion module 1002 to convert a text-based input 122 or other input into a SQL query. A text-based input 122 of “The Team1 vs Team2 finals in 2003 was particular exciting” is converted to: SELECT * FROM df WHERE team_name=“TEAM1” AND opponent=“TEAM2” AND season=‘2002-03’ AND period=2 AND playoffs=1 ORDER BY date LIMIT 10. The SQL query 1004 is used by a search module 1006 to search to the asset data 214 (i.e., the dataset) to generate filtered data 1008 by a machine-learning model 1010, e.g., by a table generation module 1012 as a table 1014; ¶0072, at least discloses the asset interaction module 226 maps the color palette onto colors of that asset. Given two histograms, e.g., one from the graphic and one from the color palette, colors are transferred via mapping to minimize an “Earth Mover Distance.” Therefore, the resulting colors preserve properties of the visualization such as categorical properties, diverging properties, line color schemes, and the like).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat to incorporate the teachings of Chan, and apply the query and colors of asset into Phogat’s teachings in order the generative AI tool identifies the plurality of colors based on the user query and colors of the one or more images.
The same motivation that was utilized in the rejection of claim 1 applies equally to this claim.
Regarding claim 4, Phogat in view of Chan, discloses the data processing system of claim 1, and further discloses wherein the generative AI tool identifies a color theme based on at least one of the user query and the one or more input images (Phogat- ¶0002, at least discloses recolor a digital design based on a color theme from a digital image. More particularly, in one or more implementations, the systems recolor a digital design based on a color theme from a digital image generated utilizing a text-to-image diffusion model; Chan- Fig. 5 shows visualizations of a “canary” and “bird” [one or more input images] that are generated based on the text-based input 122; Fig. 10 and ¶0062-0064, at least disclose the asset recommendation module 206 include a SQL conversion module 1002 to convert a text-based input 122 or other input into a SQL query. A text-based input 122 of “The Team1 vs Team2 finals in 2003 was particular exciting” is converted to: SELECT * FROM df WHERE team_name=“TEAM1” AND opponent=“TEAM2” AND season=‘2002-03’ AND period=2 AND playoffs=1 ORDER BY date LIMIT 10. The SQL query 1004 is used by a search module 1006 to search to the asset data 214 (i.e., the dataset) to generate filtered data 1008 by a machine-learning model 1010, e.g., by a table generation module 1012 as a table 1014; ¶0072, at least discloses the asset interaction module 226 maps the color palette onto colors of that asset. Given two histograms, e.g., one from the graphic and one from the color palette, colors are transferred via mapping to minimize an “Earth Mover Distance.” Therefore, the resulting colors preserve properties of the visualization such as categorical properties, diverging properties, line color schemes, and the like).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat to incorporate the teachings of Chan, and apply the query and the one or more input images into Phogat’s teachings in order the generative AI tool identifies a color theme based on at least one of the user query and the one or more input images.
The same motivation that was utilized in the rejection of claim 1 applies equally to this claim.
Regarding claim 5, Phogat in view of Chan, discloses the data processing system of claim 1, and further discloses wherein the base palette generation engine generates the base color palette (see Claim 1 rejection for detailed analysis) based on heuristics applied to the plurality of colors (Phogat- ¶0043, at least discloses the design recolor system 102 utilizes the clustering algorithm to initialize a set of color clusters with a range of colors smaller than a range of colors of the digital design 200. Specifically, the design recolor system 102 assigns colors of the digital design 200 to the set of color clusters which maintains color relationships within the digital design 200 and reduces the color palette size (e.g., the range) of the digital design 200.).
Regarding claim 6, Phogat in view of Chan, discloses the data processing system of claim 1, and further discloses wherein the base color palette includes 7 colors (Phogat- ¶0051, at least discloses a range of colors typically includes a combination of colors to create a particular feeling or aesthetic. To illustrate, a range of colors include monochromatic (e.g., shades, tints, and tones of a single base color), analogous (e.g., adjacent colors on a color wheel), complementary (e.g., colors opposite of each other on the color wheel), triadic colors (e.g., three colors evenly spaced on a color wheel), neutral colors (e.g., brown, or grey), warm colors (e.g., red, orange, yellow), or cool colors (e.g., blue, green, purple). ).
5. Claims 7-9 are rejected under 35 U.S.C. 103 as being unpatentable over Phogat in view of Chan, further in view of Lieb et al., (“Lieb”) [US-2008/0044081-A1]
Regarding claim 7, Phogat in view of Chan, discloses the data processing system of claim 1, and does not explicitly disclose, but Lieb discloses wherein each of the one or more input images is transmitted to a color map engine which extracts colors from each of the one or more input images to generate a global color list for each image (Lieb- ¶0006, at least discloses a system which can, with a high-degree of accuracy, automatically index multiple colors from each image in a set of images and then allow users to either search images using color-related keywords or browse by selecting from lists of colors which commonly appear in the image catalog; ¶0030-0037, at least disclose Each resulting color is assigned a score, based on a number of factors (including the amount of color in the source image, the average pixel position of that color, etc). Finally, each color is mapped to one-or-more colors using one-or-more “color maps” (predefined discreet sets of colors) using an algorithm […] shoppers or searchers can now search the image catalog using color. They can do this in at least one of two ways: by keyword or by selecting a color from a list [color list] […] The system is able to parse these query strings and then convert them to a list of color map values that corresponds to the text search; ¶0056, at least discloses Color match module 630 may then match color values to values of a color map 635, normalizing color values into a predictable universe of color values [global color list]; ¶0166, at least discloses First, it shows images which matched the most colors of the query. If the query is “Red and Blue”, and image A matched both colors, and image B just matched Red, image A displays first [extracts colors from each of the one or more input images]).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat/Chan to incorporate the teachings of Lieb, and apply color list into Phogat/Chan’s teachings in order each of the one or more input images is transmitted to a color map engine which extracts colors from each of the one or more input images to generate a global color list for each image.
Doing so would provide a system which can, with a high-degree of accuracy, automatically index multiple colors from each image in a set of images and then allow users to either search images using color-related keywords or browse by selecting from lists of colors which commonly appear in the image catalog.
Regarding claim 8, Phogat in view of Chan and Lieb, discloses the data processing system of claim 7, and further discloses wherein the global color list is filtered to remove neutral colors (Lieb- ¶0056, at least discloses Color match module 630 may then match color values to values of a color map 635, normalizing color values into a predictable universe of color values [global color list]; Claim 5, at least discloses filtering out greyscale color values from pixel groups of the image).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat/Chan to incorporate the teachings of Lieb, and apply filtering out greyscale color values into Phogat/Chan’s teachings in order the global color list is filtered to remove neutral colors.
The same motivation that was utilized in the rejection of claim 7 applies equally to this claim.
Regarding claim 9, Phogat in view of Chan and Lieb, discloses the data processing system of claim 8, and further discloses wherein the global color list is combined with the plurality of colors to generate a combined color list for transmission to the base palette generation engine (Phogat- ¶0119, at least discloses the series of acts 1000 includes sub-acts such as a sub-act 1008 transforming one or more colors of the recolored digital design to be within a range of the colors of the digital image; Lieb- ¶0120-0123, at least disclose The system compare all ColorGroups to each other, and merge 2 groups (ColorGroupA and ColorGroupB) […] When 2 ColorGroups are matched, their average, total position, total vertical score, etc. are all merged) .
6. Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Phogat in view of Chan, further in view of Reshetov et al., (“Reshetov”) [US-6,819,793-B1]
Regarding claim 10, Phogat in view of Chan, discloses the data processing system of claim 1, and further discloses wherein recoloring the digital artifact includes recoloring one or more elements of the digital artifact based on the base color paletterecoloring a digital design according to a digital image (e.g., a source image). To illustrate, FIG. 5 shows the digital image 500 with a cool color scheme (blues, whites, and blacks) and the recolored digital design 504 includes mostly cool colors however a sofa/couch depicted in the recolored digital design 504 includes a red color (e.g., not a cool color scheme)).
The prior art does not explicitly disclose, but Reshetov discloses
recoloring based on the base color palette in accordance with heuristics (Reshetov- col 5, lines 34-46, at least discloses A color palette generally refers to a plurality of colors that are used to color texels during texture decompression […] During texture decompression, the indexes stored for each texel are used to recolor each texel with the color represented in the palette by the index; col 19, lines 9-20, at least discloses R={rivε{0,1}, i=1 . . . N, v=1 . . . K} is the set of rules that define which entries from the global palette Y are to be taken as the local color palette entries for a texel. Thus, for a texel xi the local palette includes yv if and only if riv=1. The set of rules R may be dependent upon the local palette pattern and modifications may be required for certain local palette patterns)
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat/Chan to incorporate the teachings of Reshetov, and apply the set of rules into Phogat/Chan’s teachings for recoloring the digital artifact includes recoloring one or more elements of the digital artifact based on the base color palette in accordance with heuristics.
Doing so would allow more and higher-resolution textures to be incorporated into graphics, and provide a more realistic, immersing experience.
7. Claims 11 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Phogat et al., (“Phogat”) [US-2025/0078341-A1] in view of Hill, (“Hill”) [US-2019/0340791-A1]
Regarding claim 11, Phogat discloses a method for automatically recoloring a digital artifact to generate an aesthetically pleasing design (Phogat- ¶0002, at least discloses systems, methods, and non-transitory computer-readable media that recolor a digital design based on a color theme from a digital image; ¶0051, at least discloses the first range of colors 302 includes a set of colors (e.g., a color palette) that share a common theme or grouping based on specific requirements. Specifically, a range of colors typically includes a combination of colors to create a particular feeling or aesthetic), the method comprising:
receiving the digital artifact and one or more input images (Phogat- ¶0002, at least discloses system receives an indication of a selection of a digital design [digital artifact] and a text prompt input; Fig. 2 and ¶0037-0038, at least disclose FIG. 2 shows the design recolor system 102 receiving a digital image 202 (e.g., PNG or a JPEG) [one or more input images] generated from a text prompt 204 […] the digital image 202 includes an image designated as a source for transferring colors. Specifically, the design recolor system 102 obtains the digital image 202 by utilizing a text-to-image diffusion neural network and transfers colors from the digital image 202 to a digital design 200 (e.g., a SVG) [digital artifact]; Fig. 7 and ¶0097, at least disclose the design recolor system 102 receiving an indication of a selection within a graphical user interface of a digital design 700 [digital artifact] from a client device);
from a user interface screen of an application being executed on a user client device (Phogat- ¶0095, at least discloses the text vector representation (e.g., the text query) to generate text-conditioned images; Fig. 7 and ¶0097, at least disclose the design recolor system 102 receiving an indication of a selection within a graphical user interface of a digital design 700 from a client device [user interface screen of an application]; ¶0107, at least discloses the client device application manager 814 manages the graphical user interface for a user/designer of a client device to provide a text prompt input or for indicating the selection of a digital design (e.g., a target design)), a desire to generate the design, the design including the digital artifact and the one or more input images (Phogat- ¶0002, at least discloses system receives an indication of a selection of a digital design [digital artifact] and a text prompt input; Fig. 2 and ¶0037-0038, at least disclose FIG. 2 shows the design recolor system 102 receiving a digital image 202 (e.g., PNG or a JPEG) [one or more input images] generated from a text prompt 204 […] the digital image 202 includes an image designated as a source for transferring colors. Specifically, the design recolor system 102 obtains the digital image 202 by utilizing a text-to-image diffusion neural network and transfers colors from the digital image 202 to a digital design 200 (e.g., a SVG) [digital artifact]; Fig. 7 and ¶0097, at least disclose the design recolor system 102 receiving an indication of a selection within a graphical user interface of a digital design 700 [digital artifact] from a client device);
constructing a prompt, via a prompt construction engine, for transmission to a generative artificial intelligence (Al) tool, the prompt requesting the generative AI tool to identify an intended design transforming color features of the digital design in accordance with the color scheme of the digital image (e.g., the source image); ¶0024, at least discloses receiving, via input from a client device, a text prompt [prompt] and generating a digital image from the text prompt utilizing a text-to-image diffusion model […] the design recolor system receives a text prompt from a designer indicating specific color schemes/themes and the design recolor system generates the digital image according to the indications of the text prompt; Fig. 1 and ¶0032, at least disclose The client device 110 includes one or more applications (e.g., an image generation application) for processing text prompts and recoloring digital designs or digital images in accordance with the media management system 104; ¶0035, at least discloses the client device 110 transmits the text prompt [prompt for transmission to a generative artificial intelligence (Al) tool] with the multiple concepts to the server(s) 106. In response, the design recolor system 102 on the server(s) 106 utilizes a diffusion neural network to generate a text-conditioned image; ¶0095, at least discloses the text vector representation (e.g., the text query) to generate text-conditioned images; Fig. 7 and ¶0101, at least disclose the digital image manager 802 receives a text prompt from a designer of a client device and passes the text prompt to the text-to-image diffusion model manager 812 which then passes a digital image back to the digital image manager 802; ¶0106, at least discloses The text-to-image diffusion model manager 812 receives text prompts from the digital image manager 802 [prompt construction engine]. In particular, the text-to-image diffusion model manager 812 generates a digital image from a text prompt utilizing various denoising neural networks conditioned on the text prompt. Furthermore, the text-to-image diffusion model manager 812 [generative AI tool] pre-trains a diffusion neural network for generating text-conditioned images);
transmitting the prompt to the generative AI tool (Phogat- Fig. 7 and ¶0101, at least disclose the digital image manager 802 receives a text prompt from a designer of a client device and passes the text prompt to the text-to-image diffusion model manager 812 which then passes a digital image back to the digital image manager 802 [transmitting the prompt to the generative AI tool]);
receiving from the generative AI tool the intended design (Phogat- ¶0002, at least discloses systems recolor a digital design based on a color theme from a digital image generated utilizing a text-to-image diffusion model […] the disclosed system preserves the geometry of the digital design and takes on the digital image's look and feel by transferring the color variations of the digital image to the digital design; ¶0038, at least discloses the design recolor system 102 obtains the digital image 202 by utilizing a text-to-image diffusion neural network [generative AI tool] and transfers colors from the digital image 202 to a digital design 200 (e.g., a SVG));
and
recoloring the digital artifact based on the base color palette (Phogat- ¶0020, at least discloses digital designs contain thousands of colors and the design recolor system utilizes quantization to reduce the range of colors to a smaller range (e.g., reduce the color palette size) […] quantization improves the effectiveness of a color affine transformation (e.g., because the range of colors is reduced and color quantization results in an efficient representation of colors in an image/design); Fig. 7 and ¶0098, at least disclose the design recolor system 102 transfers colors from the digital image 706 to the digital design 700 to generate a recolored digital design 708. In particular, the design recolor system 102 utilizes a color affine transformation algorithm that recolors the digital design 700 according to the colors of the digital image 706).
Phogat does not explicitly disclose receiving a user query; the user query indicating a desire to generate the design; identify an intended design style based on the user query; transmitting the intended design style to a style to palette mapping engine to identify a plurality of colors that correspond to the intended design style; transmitting the plurality of colors to a base palette generation engine, the base palette generation engine generating a base color palette based on at least one of one or more colors of the one or more input images or the plurality of colors received from the style to palette mapping engine.
However, Hill discloses
receiving a user query (Hill- Fig. 2 and ¶0148-0150, at least disclose a question/answer based flow is shown. In set (A), the user is prompted with a design question. In step (B) the user is presented with customized options. In step (C) the user selects an option to a design question. Afterwards, the user repeats steps (A)-(C) for all questions […] the questions [query] include questions relating to color palettes, color applications in a specimen, color flows, font preferences, icon style preference, illustration style preferences, and the like);
the user query indicating a desire to generate the design (Hill- ¶0051, at least discloses the step of receiving comprises a series of questions relating to color palettes, color application in a specimen, color flows, font preferences, image style preferences, icon style preferences, illustration style preferences and a combination thereof; ¶0115, at least discloses the system and method provides various questions or topics assist a user in choosing color design preferences for a color design output; ¶0125, at least discloses The system produces a visual representation of the progress of the color design output in real-time as users satisfy each question or topic; Fig. 2 and ¶0148-0150, at least disclose a question/answer based flow is shown. In set (A), the user is prompted with a design question. In step (B) the user is presented with customized options. In step (C) the user selects an option to a design question. Afterwards, the user repeats steps (A)-(C) for all questions […] the questions [query] include questions relating to color palettes, color applications in a specimen, color flows, font preferences, icon style preference, illustration style preferences, and the like);
transmitting the intended design style to a style to palette mapping engine to identify a plurality of colors that correspond to the intended design style (Hill- ¶0051, at least discloses the step of receiving comprises a series of questions relating to color palettes, color application in a specimen, color flows, font preferences, image style preferences, icon style preferences, illustration style preferences and a combination thereof; ¶0127, at least discloses The system produces a detailed color style guide for the application of color […] system produces design style variable to be applied to pre-coded web component structures; ¶0150-0151, at least disclose the questions include questions relating to color palettes, color applications in a specimen, color flows, font preferences, icon style preference, illustration style preferences, and the like […] the final output is generated based on rules using custom generated design preferences, not on pre-existing templates or previously established design styles foreign to the user; ¶0163-0166, at least disclose computing and providing a detailed color design guide for the application of color […] computing and providing a design style variable to be applied to pre-coded web component structures […] This inventive color design flow provides the ability to assign color value-agnostic attributes to any color and allows colors to be compared and mapped across color palettes […] Also, the ability to add N number of color rules so that N possible applications of color for a given design may be produced; ¶0173-0175, at least disclose A color combination model is comprised of one or more colors, a design output type, granular inputs on assigning colors to a whole or part of a sample design output representing a design output type […] The ability to apply colors to a sample design output);
transmitting the plurality of colors to a base palette generation engine, the base palette generation engine generating a base color palette based on at least one of one or more colors of the one or more input images or the plurality of colors received from the style to palette mapping engine (Hill- ¶0157-0165, at least disclose Sources of color palettes are presented to a user for selection (A). In certain embodiments, the sources of color palettes are generated via color palette generator, manually add/selected, colors extracted from an image, colors extracted from a website or combinations thereof […] This inventive color design flow provides the ability to assign color value-agnostic attributes to any color and allows colors to be compared and mapped across color palettes; ¶0205-0206, at least disclose the system produces color palette elements based on matching criteria set forth in the color rule data […] providing any color palette elements from any source […] Alternately, the system could produce one or more color palette elements guaranteed to match the criteria to produce an outcome based on the color palette element attributes stored in one or more color rules).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat to incorporate the teachings of Hill, and apply prompting with a design question and producing design style into Phogat’s teachings for receiving a user query, from a user interface screen of an application being executed on a user client device, the user query indicating a desire to generate the design, the design including the digital artifact and the one or more input images; constructing a prompt, via a prompt construction engine, for transmission to a generative artificial intelligence (Al) tool, the prompt requesting the generative AI tool to identify an intended design style based on the user query; receiving from the generative AI tool the intended design style; transmitting the intended design style to a style to palette mapping engine to identify a plurality of colors that correspond to the intended design style; transmitting the plurality of colors to a base palette generation engine, the base palette generation engine generating a base color palette based on at least one of one or more colors of the one or more input images or the plurality of colors received from the style to palette mapping engine.
Doing so would provide methods and systems to select color design elements that are aesthetically pleasing and achieve desired results.
Regarding claim 14, Phogat in view of Hill, discloses the method of claim 11, and further discloses wherein the digital artifact is a template (Hill- ¶0058, at least discloses the design output is generated based on rules using custom generated color preferences and is not based upon pre-existing templates or previously established colors).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat to incorporate the teachings of Hill, and apply the templates into Phogat’s teachings in order the digital artifact is a template.
The same motivation that was utilized in the rejection of claim 11 applies equally to this claim.
8. Claims 12-13 are rejected under 35 U.S.C. 103 as being unpatentable over Phogat in view of Hill, further in view of Chan et al., (“Chan”) [US-2025/0278437-A1]
Regarding claim 12, Phogat in view of Hill, discloses the method of claim 11, and does not explicitly disclose, but Chan discloses wherein the generative AI tool is a large language model (Chan- ¶0003, at least discloses A text-based input is received and asset recommendation data is generated based on the text-based input using a machine-learning model, e.g., a large language model (LLM)).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat/Hill to incorporate the teachings of Chan, and apply the large language model (LLM) into Phogat/Hill’s teachings in order the generative AI tool is a large language model.
Doing so would provide large language models provides a foundational tool in artificial intelligence for understanding and generating human language, powering a wide range of applications from conversational agents to content creation tools.
Regarding claim 13, Phogat in view of Hill, discloses the method of claim 11, and does not explicitly disclose, but Chan discloses wherein the generative AI tool is a Generative Pre-trained Transformer (Chan- ¶0054, at least discloses A family of generative machine-learning models are then employed by the machine-learning model 210 of the asset recommendation module 206 to generate the different asset types […] “GPT-3.5” is usable for text completion, further discussion of which may be found at “OpenAI. 2023, https://platform.openai.com/docs/models/gpt-3-5.” [Wingdings font/0xE0] suggests a Generative Pre-trained Transformer).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat/Hill to incorporate the teachings of Chan, and apply GPT-3.5 into Phogat/Hill’s teachings in order the generative AI tool is a Generative Pre-trained Transformer.
Doing so would provide large language models provides a foundational tool in artificial intelligence for understanding and generating human language, powering a wide range of applications from conversational agents to content creation tools.
9. Claims 15 and 17-20 are rejected under 35 U.S.C. 103 as being unpatentable over Phogat et al., (“Phogat”) [US-2025/0078341-A1] in view of Hill, (“Hill”) [US-2019/0340791-A1], further in view of Lieb, (“Lieb”) [US-2008/0044081-A1]
Regarding claim 15, Phogat discloses a non-transitory computer readable medium on which are stored instructions that, when executed, cause a programmable device to perform functions (Phogat- Figs. 1, 8 and ¶0108, at least discloses the components 802-814 can include one or more instructions stored on a computer-readable storage medium and executable by processors of one or more computing devices, such as a client device or server device. When executed by the one or more processors, the computer-executable instructions of the design recolor system 102 can cause the computing device(s) to perform the methods) of:
from a user interface screen of an application being executed on a user client device (Phogat- ¶0107, at least discloses the client device application manager 814 manages the graphical user interface for a user/designer of a client device to provide a text prompt input or for indicating the selection of a digital design (e.g., a target design)), to create a design that incorporates one or more user selected images into a digital artifact (Phogat- ¶0002, at least discloses system receives an indication of a selection of a digital design [digital artifact] and a text prompt input; Fig. 2 and ¶0037-0038, at least disclose FIG. 2 shows the design recolor system 102 receiving a digital image 202 (e.g., PNG or a JPEG) [one or more input images] generated from a text prompt 204 […] the digital image 202 includes an image designated as a source for transferring colors. Specifically, the design recolor system 102 obtains the digital image 202 by utilizing a text-to-image diffusion neural network and transfers colors from the digital image 202 to a digital design 200 (e.g., a SVG) [create a design that incorporates one or more user selected images into a digital artifact]; Fig. 7 and ¶0097, at least disclose the design recolor system 102 receiving an indication of a selection within a graphical user interface of a digital design 700 [design] from a client device);
receiving the digital artifact and the one or more user selected images (Phogat- ¶0002, at least discloses system receives an indication of a selection of a digital design [digital artifact] and a text prompt input; Fig. 2 and ¶0037-0038, at least disclose FIG. 2 shows the design recolor system 102 receiving a digital image 202 (e.g., PNG or a JPEG) [one or more input images] generated from a text prompt 204 […] the digital image 202 includes an image designated as a source for transferring colors. Specifically, the design recolor system 102 obtains the digital image 202 by utilizing a text-to-image diffusion neural network and transfers colors from the digital image 202 to a digital design 200 (e.g., a SVG) [digital artifact]; Fig. 7 and ¶0097, at least disclose the design recolor system 102 receiving an indication of a selection within a graphical user interface of a digital design 700 [digital artifact] from a client device);
extracting a plurality of colors from each of one or more user selected images via a color map engine (Phogat- ¶0021, at least discloses the design recolor system utilizes a color affine transformation algorithm […] the color affine transformation algorithm includes a mechanism for extracting color features from the digital design (e.g., the target image) and the digital image and transforming color features of the digital design in accordance with the color scheme of the digital image (e.g., the source image); ¶0044, at least discloses the design recolor system 102 utilizing a color affine transformation algorithm 208. Specifically, the color affine transformation algorithm 208 includes extracting colors from the digital image 202 and the digital design 200 for transforming colors of the digital design 200 according to the digital image 202);
generating a base color palette via a base palette generation engine (Phogat- Fig. 3 and ¶0051, at least disclose the first digital design 300 contains a first range of colors 302. For instance, the first range of colors 302 includes a set of colors (e.g., a color palette) that share a common theme or grouping based on specific requirements. Specifically, a range of colors typically includes a combination of colors to create a particular feeling or aesthetic. To illustrate, a range of colors include monochromatic (e.g., shades, tints, and tones of a single base color), analogous (e.g., adjacent colors on a color wheel), complementary (e.g., colors opposite of each other on the color wheel), triadic colors (e.g., three colors evenly spaced on a color wheel), neutral colors (e.g., brown, or grey), warm colors (e.g., red, orange, yellow), or cool colors (e.g., blue, green, purple));
applying the base color palette to the digital artifact via a color application engine to recolor the digital artifact based on the base color palette (Phogat- ¶0020, at least discloses digital designs contain thousands of colors and the design recolor system utilizes quantization to reduce the range of colors to a smaller range (e.g., reduce the color palette size) […] quantization improves the effectiveness of a color affine transformation (e.g., because the range of colors is reduced and color quantization results in an efficient representation of colors in an image/design); Fig. 7 and ¶0098, at least disclose the design recolor system 102 transfers colors from the digital image 706 to the digital design 700 to generate a recolored digital design 708. In particular, the design recolor system 102 utilizes a color affine transformation algorithm that recolors the digital design 700 according to the colors of the digital image 706); and
creating the design based on the recolored digital artifact and the one or more user selected images (Phogat- ¶0002, at least discloses system receives an indication of a selection of a digital design [digital artifact] and a text prompt input; Fig. 2 and ¶0037-0038, at least disclose FIG. 2 shows the design recolor system 102 receiving a digital image 202 (e.g., PNG or a JPEG) [one or more input images] generated from a text prompt 204 […] the digital image 202 includes an image designated as a source [images] for transferring colors. Specifically, the design recolor system 102 obtains the digital image 202 by utilizing a text-to-image diffusion neural network and transfers colors from the digital image 202 to a digital design 200 (e.g., a SVG) [digital artifact]; ¶0042, at least discloses the design recolor system 102 utilizing a series of algorithms/methods to generate an enhanced recolored digital design 214. For instance, FIG. 2 shows the design recolor system 102 utilizing a clustering algorithm 206 for quantization of the digital design 200; Fig. 7 and ¶0097, at least disclose the design recolor system 102 receiving an indication of a selection within a graphical user interface of a digital design 700 [digital artifact] from a client device).
Phogat does not explicitly disclose receiving a user request to create a design; filtering the plurality of colors to remove neutral colors; generating a base color palette based on the filtered plurality of colors.
However, Hill discloses
receiving a user request to create a design (Hill- ¶0051, at least discloses the step of receiving comprises a series of questions relating to color palettes, color application in a specimen, color flows, font preferences, image style preferences, icon style preferences, illustration style preferences and a combination thereof; ¶0115, at least discloses the system and method provides various questions or topics assist a user in choosing color design preferences for a color design output; ¶0125, at least discloses The system produces a visual representation of the progress of the color design output in real-time as users satisfy each question or topic; Fig. 2 and ¶0148-0150, at least disclose a question/answer based flow is shown. In set (A), the user is prompted with a design question. In step (B) the user is presented with customized options. In step (C) the user selects an option to a design question. Afterwards, the user repeats steps (A)-(C) for all questions […] the questions [query] include questions relating to color palettes, color applications in a specimen, color flows, font preferences, icon style preference, illustration style preferences, and the like);
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat to incorporate the teachings of Hill, and apply prompting with a design question and producing design style into Phogat’s teachings for receiving a user request, from a user interface screen of an application being executed on a user client device, to create a design that incorporates one or more user selected images into a digital artifact.
Doing so would provide methods and systems to select color design elements that are aesthetically pleasing and achieve desired results.
The prior art does not explicitly disclose, but Lieb discloses
filtering the plurality of colors to remove neutral colors (Lieb- Claim 5, at least discloses filtering out greyscale color values from pixel groups of the image);
generating a base color palette based on the filtered plurality of colors (Lieb- ¶0086, at least discloses Color window 1330 allows for selection of a color from a palette or list of colors; Claim 3, at least discloses filtering out fleshtone color values from pixel groups of the image; Claim 4, at least discloses filtering out background color values from pixel groups of the image [Wingdings font/0xE0] suggests the filtered plurality of colors).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat/Hill to incorporate the teachings of Lieb, and apply filtering out greyscale color values into Phogat/Hill’s teachings for filtering the plurality of colors to remove neutral colors; generating a base color palette based on the filtered plurality of colors via a base palette generation engine.
Doing so would provide a system which can, with a high-degree of accuracy, automatically index multiple colors from each image in a set of images and then allow users to either search images using color-related keywords or browse by selecting from lists of colors which commonly appear in the image catalog.
Regarding claim 17, Phogat in view of Hill and Lieb, discloses the non-transitory computer readable medium of claim 15, and further discloses wherein the plurality of colors are provided to a global color extraction engine which generates a global color frequency list of image colors (Lieb- ¶0006, at least discloses a system which can, with a high-degree of accuracy, automatically index multiple colors from each image in a set of images and then allow users to either search images using color-related keywords or browse by selecting from lists of colors which commonly appear in the image catalog; ¶0030-0037, at least disclose Each resulting color is assigned a score, based on a number of factors (including the amount of color in the source image, the average pixel position of that color, etc). Finally, each color is mapped to one-or-more colors using one-or-more “color maps” (predefined discreet sets of colors) using an algorithm […] shoppers or searchers can now search the image catalog using color. They can do this in at least one of two ways: by keyword or by selecting a color from a list [global color frequency list] […] The system is able to parse these query strings and then convert them to a list of color map values that corresponds to the text search; ¶0056, at least discloses Color match module 630 may then match color values to values of a color map 635, normalizing color values into a predictable universe of color values [global color frequency list]).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat/Hill to incorporate the teachings of Lieb, and apply color from a list into Phogat/Hill’s teachings in order the plurality of colors are provided to a global color extraction engine which generates a global color frequency list of image colors.
The same motivation that was utilized in the rejection of claim 15 applies equally to this claim.
Regarding claim 18, Phogat in view of Hill and Lieb, discloses the non-transitory computer readable medium of claim 15, and further discloses wherein the base palette generation engine generates the base color palette based on heuristics applied to the filtered plurality of colors (Phogat- ¶0043, at least discloses the design recolor system 102 utilizes the clustering algorithm to initialize a set of color clusters with a range of colors smaller than a range of colors of the digital design 200. Specifically, the design recolor system 102 assigns colors of the digital design 200 to the set of color clusters which maintains color relationships within the digital design 200 and reduces the color palette size (e.g., the range) of the digital design 200; Lieb- ¶0086, at least discloses Color window 1330 allows for selection of a color from a palette or list of colors; Claim 3, at least discloses filtering out fleshtone color values from pixel groups of the image; Claim 4, at least discloses filtering out background color values from pixel groups of the image [Wingdings font/0xE0] suggests the filtered plurality of colors).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat/Hill to incorporate the teachings of Lieb, and apply the filtered plurality of colors into Phogat/Hill’s teachings in order the base palette generation engine generates the base color palette based on heuristics applied to the filtered plurality of colors.
The same motivation that was utilized in the rejection of claim 15 applies equally to this claim.
Regarding claim 19, Phogat in view of Hill and Lieb, discloses the non-transitory computer readable medium of claim 15, and further discloses wherein the color application engine recolors one or more elements of the digital artifact based on the base color palette (Phogat- Fig. 5 and ¶0087, at least disclose the enhanced recolored digital design 510 overcomes issues of color dullness while successfully recoloring a digital design according to a digital image (e.g., a source image). To illustrate, FIG. 5 shows the digital image 500 with a cool color scheme (blues, whites, and blacks) and the recolored digital design 504 includes mostly cool colors however a sofa/couch depicted in the recolored digital design 504 includes a red color (e.g., not a cool color scheme)).
Regarding claim 20, Phogat in view of Hill and Lieb, discloses the non-transitory computer readable medium of claim 15, and further discloses wherein the plurality of colors from each of the one or more images are combined to generate one color list (Phogat- ¶0119, at least discloses the series of acts 1000 includes sub-acts such as a sub-act 1008 transforming one or more colors of the recolored digital design to be within a range of the colors of the digital image; Lieb- ¶0120-0123, at least disclose The system compare all ColorGroups to each other, and merge 2 groups (ColorGroupA and ColorGroupB) […] When 2 ColorGroups are matched, their average, total position, total vertical score, etc. are all merged).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat/Hill to incorporate the teachings of Lieb, and apply merging 2 groups of colors into Phogat/Hill’s teachings in order the plurality of colors from each of the one or more images are combined to generate one color list.
The same motivation that was utilized in the rejection of claim 15 applies equally to this claim.
10. Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Phogat in view of Hill, further in view of Lieb, still further in view of Khodadadeh et al.,, (“Khodadadeh”) [US-2022/0237830-A1]
Regarding claim 16, Phogat in view of Hill and Lieb, discloses the non-transitory computer readable medium of claim 15, and does not explicitly disclose, but Khodadadeh discloses wherein the color map engine creates a color-based segmentation of each of the one or more images to obtain information about colors present in the image and a location of the present colors (Khodadadeh- ¶0022, at least discloses techniques perform semantic segmentation from each image and then cluster the possible color of an object using segmentation masks. For example, the sky can be blue (daytime), yellow/red (dusk/dawn), and dark (nighttime). The scene can then be recolored using palette mapping between these masks. Although these deep learning-based techniques can be effective at changing the color of interest, they need specific training data and can be only performed on low-resolution images; ¶0058, at least discloses The object detector 804 may be trained to detect a plurality of classes of objects and identify their location in an image using a bounding box. The automatic object re-colorization system 800 also includes a mask segmentation network 806. The mask segmentation network may be a machine learning model (e.g., a neural network) which receives an image and an object location (e.g., a bounding box) and outputs a binary mask, where each pixel of the mask indicates the presence or absence of the object).
It would have been obvious to one of ordinary in the art before the effective filing date of the claimed invention to have modified Phogat/Hill/Lieb to incorporate the teachings of Lieb, and apply merging 2 groups of colors into Phogat/Hill/Lieb’s teachings in order the color map engine creates a color-based segmentation of each of the one or more images to obtain information about colors present in the image and a location of the present colors.
Doing so would provide to the fully automatic color transformer network which generates the recolored image.
Conclusion
11. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. They are as recited in the attached PTO-892 form.
12. Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL LE whose telephone number is (571)272-5330. The examiner can normally be reached 9am-5pm.
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, Kent Chang can be reached at (571) 272-7667. 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.
/MICHAEL LE/Primary Examiner, Art Unit 2614
Prosecution Insights