The rapid development of computer,multimedia and Internet techniques has produced too large amount of images .Therefore, it becomes an urgent problem that how to find needed image efficiently in large-scale image database. Two effective ways has been proposed to solve the problem :one is content-based image retrieval technique which search target images by low-level content feature. The other is semantic image retrieval technique which in search of ways to get images' semantic information.In this paper, a lot research work has been done around three points: how to abstract and index low-level feature of images, how to retrieval images in semantic level, and how to fill the semantic gap by relevant feedback technique. Based on the research work , An efficient and practical image retrieval system is built which integrated the advantages of these techniques.In the system, key word networks and low-level feature table are both established for images, which realized double indexing; relevant feedback is also applied in the system. On one hand, it enables the system catch users' query intention on line by adjusting its similarity criterion automatically; on the other hand, it pass the annotations for relevant images, update weights between key words and images and fill the semantic networks, thus the system can study in long-term. Users can provide their query requirement in several different manners, the best retrieval result will be presented for the low-level feature and semantic network can cooperate properly. The experiment shows that the retrieval accuracy of the system is above 70% in few steps of relevant feedback (five times in average), and the performance could increase steadily with it been used. |