Back to results
US 12,548,197 B2Granted
Systems and methods for matching color and appearance of target coatings
AssigneeAxalta Coating Systems IP Co., LLC
InventorsLarry E. Steenhoek, Dominic V. Poerio
Life of this patent
Estimating the term…
Abstract
A system and method include receiving target image data associated with a target coating. A feature extraction analysis process is applied to the target image data to determine a target image feature. The feature extraction analysis process includes dividing the target image into sub-images which contains a plurality of target pixels. A machine learning model identifies one or more types of flakes present in the target coating using target pixel features.
Claims18
A system for matching a target coating comprising:
- a storage device for storing instructions;
- one or more data processors configured to execute instructions to:
- receive a target image of the target coating, wherein the target image comprises target image data;
- apply a feature extraction analysis process to the target image data to determine a target image feature, wherein the feature extraction analysis process includes dividing the target image into sub-images which contains a plurality of target pixels;
- determine target pixel features across the sub-images for the sub-images that are associated with different flakes,
- apply a machine learning model to generate predictions for identifying one or more types of flakes present in the target coating using the determined target pixel features across the sub-images,
- apply color expert rules to adjust predictions associated with the identification of the one or more types of flakes,
- wherein the applying of the color expert rules includes applying color analysis rules to the generated predictions to determine likelihood of one or more of the output candidate flakes being present in the sub-images of the target coating, and
- a paint mixing machine system operating within a repair body shop and dispensing paint components according to a coating formula that was determined based upon the generated predictions from the machine learning model which uses the determined target pixel features across the sub-images and based upon the further analysis by the color expert rules of the generated predictions.
6 more elements
A method of matching a target coating comprising:
- receiving, by one or more data processors, a target image of the target coating, wherein the target image comprises target image data;
- applying, by the one or more data processors, a feature extraction analysis process to the target image data to determine a target image feature, wherein the feature extraction analysis process includes dividing the target image into sub-images which contains a plurality of target pixels;
- determining, by the one or more data processors, target pixel features across the sub-images for the sub-images that are associated with different flakes,
- applying, by the one or more data processors, a machine learning model to generate predictions for identifying one or more types of flakes present in the target coating using the determined target pixel features across the sub-images,
- applying, by the one or more data processors, color expert rules to adjust predictions associated with the identification of the one or more types of flakes,
- wherein the applying of the color expert rules includes applying color analysis rules to the generated predictions to determine likelihood of one or more of the output candidate flakes being present in the sub-images of the target coating, and
- dispensing from a paint mixing machine system operating within a repair body shop paint components according to a coating formula that was determined based upon the generated predictions from the machine learning model which uses the determined target pixel features across the sub-images and based upon the further analysis by the color expert rules of the generated predictions.
4 more elements
Dependencies are inferred from the claim text.