Chromatic measures for color texture description and analysis

Abstract

Texture has been widely accepted as a feature of primary importance in computer vision. However, the majority of the research has focused on methods applied to grey-level images, where only the luminance component of the input signal is utilized. A method for describing the chromatic aspects of textures is proposed, that can be used for scene segmentation as well as classification. Experiments with synthesized and natural images justify the use of chromaticity-based measures.