# US 12,223,565 B2 · Increasing visibility of pixel patterns in images > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,223,565 B2 - Document ID: US12223565B2 - Status: Granted - Kind: B2 - Application number: 17/839,646 - Filed: 2022-06-14 - Published: 2023-12-14 - Granted: 2025-02-11 - Earliest claimed: 2022-06-14 - Assignees: Adobe Inc. - Applicants: Adobe Inc. - Inventors: Lauren Dest; Xin Wang; Nathan Baldwin; Michele Saad; Matthew May; Jose Ignacio Echevarria Vallespi; Dustin Ground - Web page: https://patentgrep.com/patent/US12223565B2 ## CPC - G06T 11/10: Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) - G06T 5/90: Dynamic range modification of images or parts thereof - G06T 7/11: Region-based segmentation - G06T 7/90: Determination of colour characteristics - G06V 10/235: {based on user input or interaction} - G06V 10/56: relating to colour - G06V 10/762: using clustering, e.g. of similar faces in social networks - G06T 2200/24: involving graphical user interfaces [GUIs] - G06T 2207/10024: Color image - G06T 2207/20021: Dividing image into blocks, subimages or windows - G06T 2207/20081: Training; Learning - G06T 2207/20104: Interactive definition of region of interest [ROI] - G06T 2207/30196: Human being; Person - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Methods and systems disclosed herein relate generally to increasing visibility of pixel patterns of an image. The system includes a pattern-detection application accessing an image depicting an object. The pattern-detection application determines a set of colors from the transformed image. The pattern-detection application identifies a set of pixels depicting a particular color of the set of colors. For the set of pixels depicting the particular color, the pattern-detection application converts an initial set of pixel values of the set of pixels at an initial color space to another set of pixel values that define the particular color of the set of pixels in another color space. The pattern-detection application modifies one or more values of the other set of pixel values to generate a modified set of pixel values. The modification includes causing the set of pixels visually indicate a simulated color that is different from the particular color. ## Claims ### Claim 1 A computer-implemented method comprising: accessing, by a pattern-detection application, an image depicting an object; applying, by the pattern-detection application, a machine-learning model to the image to generate a transformed image, wherein generating the transformed image includes modifying one or more pixels of the image to reduce color distortions from the image; determining, by the pattern-detection application, a set of colors from the transformed image; identifying, by the pattern-detection application, a set of pixels depicting a particular color of the set of colors; converting, by the pattern-detection application, an initial set of pixel values of the set of pixels at an initial color space to another set of pixel values that define the particular color of the set of pixels in another color space; modifying, by the pattern-detection application, one or more values of the other set of pixel values to generate a modified set of pixel values, wherein the modifying includes causing the set of pixels visually indicate a simulated color that is different from the particular color; and outputting, by the pattern-detection application, the set of pixels depicting the simulated color to be displayed on a display device. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein determining the set of colors from the transformed image includes: applying, by the pattern-detection application, a clustering algorithm to the transformed image to assign each pixel of the transformed image to a respective cluster of a set of clusters; and for each cluster of the set of clusters: determining, based on the assigned pixels and by the pattern-detection application, a centroid for the cluster; determining, by the pattern-detection application, a color represented by the centroid of the cluster; and assigning, by the pattern-detection application, the color as being one of the set of colors. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, wherein the clustering algorithm includes a k-medoids algorithm. ### Claim 4 (depends on 2) The computer-implemented method of claim 2, wherein the clustering algorithm includes a k-means algorithm. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein identifying the set of pixels depicting the particular color includes: for each color of the set of colors: determining, by the pattern-detection application, a color-difference metric between a pixel of the transformed image and a color value identifying the color; and associating, by the pattern-detection application, the color-difference metric for the color; determining, from the set of colors and by the pattern-detection application, that the particular color has the lowest color-difference metric relative to other colors of the set of colors; and assigning, by the pattern-detection application, the pixel as being one of the set of pixels for the particular color. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, further comprising: generating, by the pattern-detection application, an image layer; assigning, by the pattern-detection application, pixel values of the set of pixels to the image layer; and applying, by the pattern-detection application, the image layer to the image to generate a segmented image, wherein the segmented image identifies the set of pixels while masking other pixels of the set of pixels. ### Claim 7 (depends on 6) The computer-implemented method of claim 6, further comprising outputting, by the pattern-detection application, the image layer for displaying the image layer on a user interface. ### Claim 8 (depends on 6) The computer-implemented method of claim 6, wherein assigning the pixel values of the set of pixels to the image layer includes receiving a user input that identifies one or more regions in the image, wherein the one or more regions include the set of pixels. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein: the initial color space is a Red, Green, Blue (RGB) color space or a Hue, Saturation, Brightness (HSB) color space; and the other color space is an L*a*b* color space. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, wherein modifying the one or more values of the other set of pixel values includes modifying a pixel value associated with an L* channel of the L*a*b* color space. ### Claim 11 (depends on 1) The computer-implemented method of claim 1, wherein a first contrast ratio between the simulated color and another color of the set of colors is greater than a second contrast ratio between the particular color and the other color. ### Claim 12 A system comprising: a color-identification module configured to: access an image depicting an object; apply a machine-learning model to the image to generate a transformed image, wherein generating the transformed image includes modifying one or more pixels of the image to reduce color distortions from the image; and determine a set of colors from the transformed image; a segmentation module configured to: access the image and the determined set of colors; and identify a set of pixels depicting a particular color of the set of colors; and a color-conversion module configured to: access the set of pixels; convert an initial set of pixel values of the set of pixels at an initial color space to another set of pixel values that define the particular color of the set of pixels in another color space; and modify one or more values of the other set of pixel values to generate a modified set of pixel values, wherein the modifying includes causing the set of pixels visually indicate a simulated color that is different from the particular color. ### Claim 13 (depends on 12) The system of claim 12, wherein determining the set of colors from the transformed image includes: applying a clustering algorithm to the transformed image to assign each pixel of the transformed image to a respective cluster of a set of clusters; for each cluster of the set of clusters: determining, based on the assigned pixels, a centroid for the cluster; determining a color represented by the centroid of the cluster; and assigning the color as being one of the set of colors. ### Claim 14 (depends on 12) The system of claim 12, wherein identifying the set of pixels depicting the particular color includes: for each color of the set of colors: determine a color-difference metric between a pixel value of a pixel of the transformed image and a color value identifying the color; and associate the color-difference metric for the color; determine, from the set of colors, that the particular color has the lowest color-difference metric relative to other colors of the set of colors; and assign the pixel as being one of the set of pixels for the particular color. ### Claim 15 (depends on 12) The system of claim 12, wherein the segmentation module is further configured to: generate an image layer; assign pixel values of the set of pixels to the image layer; and apply the image layer to the image to generate a segmented image, wherein the segmented image identifies the set of pixels while masking other pixels of the set of pixels. ### Claim 16 (depends on 12) The system of claim 12, wherein: the initial color space is a Red, Green, Blue (RGB) color space or a Hue, Saturation, Brightness (HSB) color space; and the other color space is an L*a*b* color space. ### Claim 17 (depends on 12) The system of claim 12, wherein modifying the one or more values of the other set of pixel values includes modifying a pixel value associated with an L* channel of the L*a*b* color space. ### Claim 18 (depends on 12) The system of claim 12, wherein a first contrast ratio between the simulated color and another color of the set of colors is greater than a second contrast ratio between the particular color and the other color. ### Claim 19 A non-transitory computer-readable medium storing processor-executable instructions configured to cause one or more processors to perform actions including: receiving an image depicting an object; a step of generating a simulated color for a set of pixels of the image, wherein the simulated color is generated by: (i) processing the image using a machine-learning model to reduce color distortions from the image; (ii) identifying a particular color from the processed image; (iii) identifying the set of pixels depicting the particular color; and (iv) modifying pixel values of the set of pixels to depict the simulated color that is different from the particular color; and outputting the set of pixels depicting the simulated color to be displayed on a display device. ### Claim 20 (depends on 19) The non-transitory computer-readable medium of claim 19, wherein a first contrast ratio between the simulated color and another color of the image is greater than a second contrast ratio between the particular color and the other color.