Region-based image retrieval: fast coarse segmentation and fine color description

The two major problems raised by a region-based image retrieval system are the automatic detection and visual description of regions. We adopt a coarse detection and fine description approach. In this paper we first present a new method of unsupervised coarse detection which provides intuitive and visually characteristic regions of interest. This segmentation scheme is based on the classification of local distributions of quantized colors (LDQC). The Competitive Agglomeration classification algorithm is used which has the advantage to automatically determine the number of classes. Then, considering that description must be finer for regions than for images, we propose a new region descriptor of fine color variability: the adaptive distribution of color shades (ADCS). Combined with an appropriate similarity measure, the high color resolution of ADCS improves the perceptual similarity of retrieved regions compared to existing color descriptors. (C) 2003 Elsevier Ltd. All rights reserved.