Content-Based Image Retrieval using color and edge direction features

Abstract

This paper presents an novel technique that employs both the color and edge direction features for Content-Based Image Retrieval (CBIR). In this method, a given image is first divided into sub-block which has the same size and then the color and edge direction features of each sub-block can be extracted. Next, it constructs a codebook of color feature using clustering algorithm and then each sub-block is mapped to the codebook. Finally, it uses the color index codes to image retrieval and uses the edge direction feature as the color feature's weight which belongs to the same color feature's sub-block. The effectiveness of this technique is demonstrated with the experiments.