基于压缩域的图像检索技术  

Image Retrieval Technique in the Compressed Domain: A Review

作　　者：李晓华[1] 沈兰荪[1] 

机构地区：[1]北京工业大学信号与信息处理研究室,北京100022

出　　处：《计算机学报》2003年第9期1051-1059,共9页Chinese Journal of Computers

基　　金：国家自然科学基金 ( 60 172 0 45 );北京市自然科学基金 ( 4 0 0 2 0 0 2 )资助

摘　　要：图像检索技术是多媒体应用中的关键技术 .现有的基于内容图像检索技术大都是基于非压缩域的 .对于目前普遍存在的压缩格式图像 ,采用这种技术必须先解压再检索 ,不但计算量大 ,而且需占用较多的中介存储空间 ,所以严重影响了检索系统的实时性和灵活性 .同时各种压缩标准 (如JPEG ,MPEG ,JPEG2 0 0 0等 )的推出与普及也促使人们寻求可以直接在压缩域操作的检索技术 .该文对现有的压缩域图像检索技术的发展进行综述 。Image retrieval techniques are crucial in multimedia applications. A number of retrieval techniques that operate in the pixel domain have been reported in the literature. However, the large volumes of visual data necessitate the use of compression techniques. Hence, the visual data in future multimedia databases is expected to be stored in the compressed form. In order to obviate the need to decompress the image data and then apply traditional pixel domain retrieval techniques, it is efficient to index the image in the compressed domain. At the same time, the advent of compression standards has also led to the proliferation of retrieval techniques in the compressed domain. Comparing with traditional decompress process approach which applies the pixel domain retrieval techniques, these techniques have a lower cost for computing and storing the indices. This paper presents a critical review on the compressed domain retrieval techniques proposed in the literatures. In addition, the future promising directions are also discussed.

关 键 词：图像检索 压缩域 图像纹理 图像处理 离散傅立叶变换域 计算机 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]