The Research About Feature Description And Retrieval Technology Of Image Based On MPEG-7

With the development of computer and communication technology, Multimedia data (such as video, audio and image) is increasing in a greatly increasing speed. So it is obviously important for us that how to store and search this huge data more efficiently. MPEG-7 (Multimedia Content Description Interface) will establish a variety of standard descriptive methods of multimedia information; the description has tight relation with information content, and will support rapid and effective access and locate to material that attracts the users. It requires rapid and effective retrieval services based on content, efficient data organization and correlative materials quickly location. For this reason, MPEG-7 technology may play an important role in many aspects, such as supplying metadata to describe contents and semantic meaning of multimedia, accomplishing the accession to materials through Mink and expanding the capacity of search of information from multimedia. In this paper, the application of MPEG-7 in content description generation and information retrieval of video has been systematically studied.First this article introduces the background and the research content of the problem. Then, it describes the technologies and standards relevant to content-Based-Retrieval. Then, it introduces the image retrieval system and the key technologies and puts forwards the design of multimedia content description schema based on MPEG-7. Then the following part we research the description document in MPEG-7, and research the generation of description document and how to translate the XML document to RDBMS as emphases. After that, we illustrates the idea and implementation of image match and image retrieval, the design of interface for search and the way to use the CBR system based on image .It shows the feasibility and practicability of this system. The emphasis of this article is how to describe the multimedia content and realize the descriptive documents using the encapsulation of class in Object Oriented; how to store and retrieve the XML document. In the end, some deficiencies of this scheme that need to be improved and the trends of technology in the future are pointed out.