# US 2019/0172228 A1 · Systems and methods for matching color and appearance of target coatings > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0172228 A1 - Document ID: US20190172228A1 - Status: Published application - Kind: A1 - Application number: 15/833,597 - Filed: 2017-12-06 - Published: 2019-06-06 - Earliest claimed: 2017-12-06 - Assignees: Axalta Coating Systems IP Co., LLC - Applicants: Axalta Coating Systems IP Co., LLC - Inventors: LARRY E. STEENHOEK; ALESSIO TAMBURRO - Web page: https://patentgrep.com/patent/US20190172228A1 ## CPC - G01J 3/463: {Colour matching} - G01J 3/46: Measurement of colour; Colour measuring devices, e.g. colorimeters (measuring colour temperature G01J5/60) - G06F 16/51: Indexing; Data structures therefor; Storage structures - G06F 16/535: Filtering based on additional data, e.g. user or group profiles - G06F 16/5838: {using colour} - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N 20/20: Ensemble learning - G06T 7/001: {using an image reference approach} - G06T 7/33: using feature-based methods - G06T 7/90: Determination of colour characteristics - G06V 10/56: relating to colour - G06V 10/757: {Matching configurations of points or features} - H04N 1/6008: {with primary colour signals, e.g. RGB or CMY(K)} - H04N 1/6047: {wherein the test pattern is part of an arbitrary user image} - G06T 2207/10024: Color image - G06T 2207/20081: Training; Learning - G06T 2207/30108: Industrial image inspection - G06T 2207/30156: Vehicle coating - H04N 1/6052: {Matching two or more picture signal generators or two or more picture reproducers} - G01J: MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY (light sources F21, H01J, H01K, H05B; investigating properties of materials by optical means G01N) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract System and methods for matching color and appearance of a target coating are provided herein. The system includes an electronic imaging device configured to receive a target image data of the target coating. The target image data includes target coating features. The system further includes one or more feature extraction algorithms that extracts the target image features from the target image data. The system further includes a machine-learning model that identifies a calculated match sample image from a plurality of sample images utilizing the target image features. The machine-learning model includes pre-specified matching criteria representing the plurality of sample images for identifying the calculated match sample image from the plurality of sample images. The calculated match sample image is utilized for matching color and appearance of the target coating ## Claims ### Claim 1 A processor-implemented system for matching color and appearance of a target coating, the system comprising: a storage device for storing instructions for performing the matching of color and appearance of the target coating; and one or more data processors configured to execute the instructions to: receive, by one or more data processors, target image data of the target coating, the target image data generated by an electronic imaging device and including target image features; retrieve, by one or more processors, one or more feature extraction algorithms that extract the target image features from the target image data; apply the target image data to the one or more feature extraction algorithms; extract the target image features from the target image data utilizing the one or more feature extraction algorithms; retrieve, by one or more data processors, a machine-learning model that identifies a calculated match sample image from a plurality of sample images utilizing the target image features, wherein the machine-learning model includes pre-specified matching criteria representing the plurality of sample images for identifying the calculated match sample image from the plurality of sample images; apply the target image features to the machine-learning model; and identify the calculated match sample image based upon substantially satisfying one or more of the pre-specified matching criteria; wherein the calculated match sample image is utilized for matching color and appearance of the target coating. ### Claim 2 (depends on 1) The system of claim 1, wherein the system further comprises an image database, the image database includes the plurality of sample images, and the one or more data processors are configured to execute the instructions to extract sample image features from the plurality of sample images utilizing the one or more feature extraction algorithms. ### Claim 3 (depends on 2) The system of claim 2, wherein the one or more data processors are configured to execute the instructions to generate the pre-specified matching criteria based on the sample image features. ### Claim 4 (depends on 3) The system of claim 3, wherein the one or more data processors are configured to execute the instructions to train the machine-learning model based on the plurality of sample images by generating the pre-specified matching criteria based on the sample image features. ### Claim 5 (depends on 1) The system of claim 1, wherein the target image data defines RGB values representative of the target coating, and wherein the one or more data processors are configured to execute the instructions to transform the RGB values to L*a*b* values representative of the target coating. ### Claim 6 (depends on 5) The system of claim 5, wherein the target image features comprise representations based on image entropy, and wherein the one or more feature extraction algorithms are configured to identify the representation based on image entropy for extracting the target image features from the L*a*b* values of the target image data. ### Claim 7 (depends on 1) The system of claim 1, wherein the target image features comprise representations based on image entropy, and wherein the one or more feature extraction algorithms are configured to identify the representation based on image entropy for extracting the target image features. ### Claim 8 (depends on 14) The system according to claim 14, wherein the calculated match sample image corresponds to a coating formula. ### Claim 9 (depends on 1) The system of claim 1, wherein the electronic imaging device further comprises a display configured to display the calculated match sample image. ### Claim 10 (depends on 9) The system of claim 9, wherein the display is further configured to display an image of the target coating adjacent the calculated match sample image. ### Claim 11 (depends on 10) The system of claim 10, wherein the display is further configured to display one or more alternate match sample images related to the calculated match sample image. ### Claim 12 (depends on 7) The system of claim 7, wherein the representations based on image entropy are representations based on Shannon entropy. ### Claim 13 (depends on 11) The system of claim 11 further comprising a user input module configured to select, by a user, a visual match sample image from the calculated match sample image and the one or more alternate match sample images based on an observed similarity to the image of the target coating by the user. ### Claim 14 (depends on 1) The system of claim 1, wherein the machine-learning model comprises a random decision forest algorithm including the plurality of pre-specified matching criteria. ### Claim 15 A method for matching color and appearance of a target coating, the method comprising: receiving, by one or more data processors, target image data of the target coating, the target image data generated by an electronic imaging device and including target image features; retrieving, by one or more processors, one or more feature extraction algorithms that extracts the target image features from the target image data; applying the target image data to the one or more feature extraction algorithms; extracting the target image features from the target image data utilizing the one or more feature extraction algorithms; retrieving, by one or more data processors, a machine-learning model that identifies a calculated match sample image from a plurality of sample images utilizing the target image features, wherein the machine-learning model includes pre-specified matching criteria representing the plurality of sample images for identifying the calculated match sample image from the plurality of sample images; applying the target image features to the machine-learning model; and identifying the calculated match sample image based upon substantially satisfying one or more of the pre-specified matching criteria; wherein the calculated match sample image is utilized for matching color and appearance of the target coating. ### Claim 16 (depends on 15) The method of claim 15 further comprising the step of generating the machine-learning model based on the plurality of sample images, the step of generating the machine-learning model including: retrieving the plurality of sample images from an image database; extracting sample image features from the plurality of sample images utilizing the one or more feature extraction algorithms; and generating the pre-specified matching criteria based on the sample image features. ### Claim 17 (depends on 15) The method of claim 15, wherein the electronic imaging device includes a display and wherein the method further comprises the steps of: displaying, on the display; the calculated match sample image, one or more alternate match sample images related to the calculated match sample image, and an image of the target coating adjacent the calculated match sample image and the one or more alternate match sample images; and selecting, by a user, a visual match sample image from the calculated match sample image and the one or more alternate match sample images based on an observed similarity to the target image data. ### Claim 18 (depends on 17) The method of claim 17, wherein the calculated match sample image corresponds to a primary coating formula and the one or more alternate match sample images correspond to alternate coating formulas related to the primary coating formula. ### Claim 19 (depends on 15) The method of claim 15 wherein the machine-learning model comprises a random decision forest algorithm including the plurality of pre-specified matching criteria. ### Claim 20 (depends on 15) The method of claim 15 further wherein extracting the target image features comprises extracting the target image features based on image entropy, and wherein the one or more feature extraction algorithms are configured to identify the representation based on image entropy for extracting the target image features.