An intelligent image retrieval system by integrating multiple features with a fuzzy adaptive resonance theory network

Abstract

In this paper, we present an intelligent image retrieval system by a fuzzy adaptive resonance theory (ART) network to integrate multiple features. Our system can retrieve five types of digital images, such as binary images, gray artificial vector images, gray complex background images, color artificial vector images, and color natural scene images. In the system, we separate the color information from an input image first. Then we adopt an edge detector to obtain the contours of objects from the intensity information of the image. From the edgedetected image, we find the object of the most sized contour and remove the background, which serves as the main part to represent the whole image content. Of this main part, we can extract four kinds of feature data: moment invariants, Fourier descriptors, color bins, and inside contours number that are used as the indices in our image database. For different types of images, the indices are combined with various weights. Through a fuzzy ART network to integrate the indices, our system can cluster similar images automatically after they have been processed and stored in the same way into the image database. The experimental results reveal that our approach is feasible and effective.