A content based image retrieval system based on the fuzzy ARTMAP architecture

This study deals with designing a flexible feature space for content based image retrieval systems (CBIR). Initially, a large variety of features are extracted from the regions of the pre-segmented images. Then, the feature set of each object class is learned using the fuzzy ARTMAP architecture, by identifying the weights of each feature for each object class. In the querying phase, a trained set of feature weights is used to find the membership value of each object class. This task is achieved by combining the regions in each image and computing the maximum membership value for the compound regions which correspond to a possible object class.