ABSTRACT
In design and development of any Content Based Image Retrieval (CBIR) system, feature extraction from image plays a vital role. Color, texture and shape are three important features that can used to represent an image. Efficiency of CBIR system is depends on feature extraction which effectively represents image contents. Instead of focusing on single feature, most of the recent CBIR system uses combinations of these features to represent an image. This paper introduces the concept and area of content based image retrieval system. It also includes the overview of basic MPEG-7 visual feature descriptor; edge histogram descriptor (EDH) to extract the contents from images. To enhance the result of CBIR system, the methodology combines color moments, color-correlogram and Gabor texture features along with edge orientation histogram.
