Abstract
Content-based image retrieval (CBIR) has been a worthwhile topic for research for several years. A powerful CBIR system should minimize the semantic gap between the low-level features and high-level concepts in order to satisfy users requirements. Moreover, it should take into consideration the execution time. In this paper, we present a new semantic approach for CBIR supported by a parallel aggregation of content-based features extraction (shape, texture, color) using fuzzy support decision mechanisms. Shape features are based on Fast Beta Wavelet Network modeling and Hue moments. The texture descriptor is based on Energy computing at different decomposition levels. Finally, we present an implementation of a new color feature extraction based on fuzzy indexed color map. In the second stage, we propose a Fuzzy Decision Support System for feature (shape, texture, color) aggregation to improve the retrieval performance. The proposed approach is tested on four most popular datasets: Wang, INRIA Holidays, UKBench and samples from ImageNet, and the experiments showed that the proposed approach can achieve a satisfactory retrieval performance with an acceptable search time.