Image retrieval based on improved MCD and EHD of MPEG-7

CBIR (Content-Based Image Retrieval) is a comprehensive technology which retrieves image on the basis of the content feature of images. Its main idea is to analyze the content feature of images in order to find the images with similar content in image database. CBIR has become a heated research area, for it combines image processing, pattern identification, computer vision, artificial intelligence and database together. Characteristics description based on image can only partly reflect the trait of the image, which will directly influence the retrieval effect. Considering color and texture being two most important visual feature, this paper suggests a new retrieved algorithm which comprehensively utilizes the improved MPEG-7 dominant color histogram and edge histogram and evaluates the retrieving results with the criteria provided by MPEG-7. Experiments have shown that, the retrieving results with above-mentioned feature have a better visual effect and retrieving effect.