Abstract: This document describes Content based Image Retrieval(CBIR) is a technique for retrieving images on the basis of automatically-derived features like edge for database images. It shows how Edge Histogram Descriptor of MPEG-7 can be efficiently utilized for matching of images. In this paper, we propose to use the global and semi-local edge histograms generated directly from the local histogram bins to increase the matching performance. Then, the global and local histograms of two images are compared to evaluate the similarity measure. Thus we exploit the absolute locations of edges in the image as well as its global composition. The proposed matching method is considered to be a more image content-based retrieval.

Keywords: Image retrieval, edge feature, edge histogram, similarity matching.