论文部分内容阅读
如今,越来越多的声像信息以数字形式存储和传输,这为人们更灵活地使用这些信息提供了可能性。但随着网络上信息的爆炸性增长,我们获取感兴趣信息的难度却越来越大,而传统的基于关键字或文件名的检索方法显然不适于数据量庞大且不具有天然结构特征的声像数据。因此,近年来多媒体研究的一个热点是声像数据基于内容的检索,实现这种基于内容检索的一个关键性的步骤是要定义一种描述声像信息内容的格式,而这与声像信息的存储形式(编码)密切相关。MPEG组织在推出了影响极大的MPEG-1、MPEG-2,且尚未完成MPEG-4的最后定稿就已开始着手制订专门支持多媒体信息基于内容检索的编码方案MPEG-7。MPEG-7作为MPEG家庭中的一个新成员,即
Today, more and more audiovisual information is stored and transmitted digitally, providing the possibility for people to use the information more flexibly. However, with the explosive growth of information on the Internet, it is more and more difficult for us to obtain the information of interest. However, the traditional search method based on keywords or file names is obviously not suitable for audiovisuals with large data volume and no natural structural features data. Therefore, a hot spot in multimedia research in recent years is the content-based retrieval of audiovisual data. A key step towards such content-based retrieval is to define a format for describing the content of audiovisual information, The form of storage (coding) is closely related. MPEG Organizations has started work on MPEG-7, a content-based encoding scheme specifically designed to support multimedia information, with the introduction of the most influential MPEG-1, MPEG-2 and the unfinished finalization of MPEG-4. MPEG-7 as a new member of the MPEG family, that is