Content Based Image Retrieval Technology Research

With the development of computer science and technology, the application of Internet and the rapid increment of multimedia database, we have a lot of digital images and video information. In order to manage and retrieve those information, the CBIR(Content-Based Image Retrieval) has emerged to be one of the hot research areas in image domain.In this dissertation, lots of exploratory research work has been done around some key techniques of CBIR. The main contributions of this dissertation are summarized as follows:(1) A new robust color image retrieval based on significant bit-plane is proposed according to the noise attack characteristic. Firstly, the significant bit-planes are extracted from the color image based on bit-plane theory and the noise attack characteristic. Secondly the color and spatial information of image are extracted as features for retrieval. It can retrieve the noise (including fuzzy, sharpen, and illumination, etc) image effectively.(2)A content-based color image retrieval method using SVR (Support Vector Regression) classification is proposed. Firstly, the color feature, spatial feature and texture feature are extracted from the color image as the eigenvectors. Then, the SVR are trained for natural image classification. Finally, the resulting image class model is incorporated into image retrieval system. Experimental results show that the proposed scheme is more accurate and efficient in retrieving the user-interested images.