Research Of Feature Exaction In Content-Based Image Retrieval

With the rapid development of internet and technologies of computer and multimedia, information of all kinds of images becomes more and more great. It is very important to organize, manage and utilize this multimedia information, which makes content-based image retrieval (CBIR) becomes one of the most active research focuses of implementation of multimedia. Until now, there are still many problems of this research area to be solved. This thesis focuses on the image feature exaction of content-based image retrieval (CBIR). The main content of this thesis are summarized as follows:1. The present situation and problems of the CBIR are deeply analyzed. Moreover, we discuss the principle and key techniques of CBIR.2. The exacting of color feature is researched. A hybrid measure based on color histogram is presented, in this method, accumulative histogram is used to obtain the color information of total image; Sub-blocks color moments are used to obtain the space information; Grey level histogram is used to reduce the effect of the changing of thickness and contrast; Moreover, we propose a retrieval method based on interest region, which could search the image that is partially similar...