User Interest Model-based Image Retrieval Technique

The content-based image retrieval (CBIR) system establishes the feature space by comprehending the content of an image and executing retrieval by measuring the similarity of images. With the development of CBIR, however, there are two problems. One is that since different researchers use different feature spaces, or use the same feature space but different description, then the measure is different, it is difficult for retrieval to be universal, especially in WEB. Another is that currently CBIR tools designed for satisfying the needs of all users, special needs of individual user are not considered. Aimed at above problems, we establish the multi-feature spaces, by features of color layout descriptor and homogeneous texture descriptor, which considering both color and texture by human sense, and adjusting the weight of every feature space by applying PGA (parallel genetic algorithm) for matching the user interest. The result of experiment shows that the system is robust in general format by using MPEG-7, and can match the user profile as well.