Region entropy-based image retrieval

This paper proposes a novel algorithm for image retrieval based on region entropy, which divides an image into higher and lower entropy regions and extracts the color and shape features with each type of regions. The retrieval procedure consists of two steps: first, a simple retrieval algorithm in terms of entropy feature is applied to all the images in the database, and secondly, only the results of the previous retrieval are searched. Experimental results show that the proposed method has sound and robust retrieval performance to the images with simple foreground or complex foreground.