综合分块主色和相关反馈技术的图像检索方法  

An Approach to Combining Dominant Color of Partition with Relevance Feedback in Image Retrieval

作　　者：何清法[1] 李国杰[2] 

机构地区：[1]国家智能计算机研究开发中心,北京100080 [2]中国科学院计算技术研究所高性能计算研究室,北京100080

出　　处：《计算机辅助设计与图形学学报》2001年第10期912-917,共6页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家"九七三"基础研究项目 ( 9990 10 )资助

摘　　要：图像数据的无序激增使得基于内容的图像检索技术成为研究热点 .为了克服普通颜色特征不考虑颜色的空间分布的缺点 ,提出了一种多分辨率分块主色法的空间颜色索引技术 ;同时 ,还将相关反馈技术融合到多分辨率分块主色算法中 ,以改善检索效果 .据此 ,实现了一个图像检索原型系统—— Sm art Eye,并依据所设计的评价实验 ,将 Smart Eye的检索结果与其它相关的方法进行了比较和分析 .实验表明 。Content based image retrieval becomes a hot research topic due to the rapid increase of out of order image data. In order to solve the problem of lacking the spatial knowledge of common color features, this paper presents a spatial color indexing approach using the dominant colors of multi resolution partitions. Meanwhile, the technology of relevance feedback is combined with the presented algorithm to enhance the effectiveness of retrieval. A prototype system, namely SmartEye, was implemented. Also, two experiments were designed to evaluate the effectiveness of the approach. Comparison of the retrieval results of SmartEye to that of other systems shows that the proposed approach is effective.

关 键 词：图像检索 多分辨率划分 主色 相似性测度 相关反馈 图像处理 

分 类 号：TN911.73[电子电信—通信与信息系统] TP391.41[电子电信—信息与通信工程]