A knowledge-based environment for assessment of color similarity

Abstract

A discussion is given on a knowledge-based approach to the representation and implementation of the similarity evaluation of colors; all the aspects involved in color description and the relationships between color descriptions and similarity judgments may be explicitly represented in a quantitative, rigorous and reliable way. The authors choose CIELUV, which provides a flexible and powerful numerical description of color appearance, as the color description space and fuzzy logic as the knowledge representation language for modelling human judgments in the universe of discourse of CIELUV measures. An explanatory example of color image retrieval based on similarity measure is provided to aid the presentation of tools and strategies of the knowledge-based environment.<>