Color in Databases: Indexation and Similarity

Color has been widely used for content-based image and video retrieval. However its robustness, effectiveness, and efficiency in image indexing are still open issues. The definition of feature similarity also plays a fundamental role in content-based retrieval, as images with "similar" feature distributions are considered similar in appearance without requiring any semantic expression of this. This paper reviews the methods for color image indexing and retrieval described in the literature. In particular, the features used to represent color information and the measures adopted to compute the similarity between the features of two images are critically analyzed.