An improved approach of CBIR using Color based HSV quantization and shape based edge detection algorithm

Retrieving images from the large amount of database based on their content are called content based image retrieval. It is a basic requirement of retrieve the relevant information from huge amount of image database according to query image with better system performance. Color and shape feature of image is most widely used feature to analyze the image. In this paper, proposed method is integrating HSV color histogram feature and shape based Prewitt edge detection feature of image. By analyzing the property of HSV color space, quantize this HSV color space into 72 no. of non-uniform bins based on color histogram and Prewitt edge detection technique is employed to find out meaningful transition of image. This generated quantization value of color histogram and edge feature combined and for similarity measurement Manhattan distance is used. This retrieval system applied on 500 images of Wang database which show that the combined feature performs well in precision and adaptability.