Selection of the Best Representative Feature and Membership Assignment for Content-Based Fuzzy Image Database

Abstract

A major design issue in content-based image retrieval system is the selection of the feature set. This study attacks the problem of finding a discriminative feature for each class, which is optimal in some sense. The class-dependent feature is, then, used to calculate the membership value of each object class for content-based fuzzy image retrieval systems. The Best Representative Feature (BRF) for each class is identified in a training stage. Then, using the BRF of each object class, the segment groups in the images are labeled by the membership values of each object class. The segment groups are obtained in a greedy algorithm by minimizing the distance between each training object and the segment groups, using the BRF. This minimum distance is taken as the membership value of the training object for that particular segment group. Finally, the query object is matched to each segment group in a fuzzy database using the membership values of segment groups. The BRF is selected among the MPEG-7 descriptors. The proposed scheme yields substantially better retrieval rates compared to the available fixed feature content-based image retrieval systems.