Detection of colors in an image is an important task in many contexts. For example, providers of website hosting services can recommend theme colors for a website based on a logo that is featured on the website. Prior color detection techniques have various shortcomings. For example, prior techniques often detect colors that lack chroma that are unsuitable as website theme colors; identify multiple perceptually similar colors; fail to detect a dominant color or detect colors that do not exist in the image. Further, the techniques make detection errors in the presence of image features such as shadows, anti-aliasing gradients, or compression artifacts.
This disclosure describes computationally inexpensive techniques to accurately detect and return an optimal number of perceptually distinct dominant colors in an image. The techniques are robust in the presence of noise and artifacts in the image, e.g., shadows, anti-aliasing, or use of image compression.
Krejci, Zachary, "Detection of perceptually dominant colors in images", Technical Disclosure Commons, (August 28, 2017)