发掘相关反馈日志中关联信息的图像检索方法-软件学报.PDFVIP

1000-9825/2004/15(01)0041 ©2004 Journal of Software 软 件 学 报 Vol.15, No.1 ∗ 发掘相关反馈日志中关联信息的图像检索方法 + 张 亮 , 施伯乐, 周向东, 刘 莉, 张 琪 (复旦大学 计算机与信息技术系,上海 200433) Enhancing Content-Based Image Retrieval by Exploiting Relevance Feedback Logs + ZHANG Liang , SHI Bai-Le, ZHOU Xiang-Dong, LIU Li, ZHANG Qi (Department of Computing and Information Technology, Fudan University, Shanghai 200433, China) + Corresponding author: Phn: +86-21 E-mail: zhangl@, Received 2002-09-04; Accepted 2003-03-04 Zhang L, Shi BL, Zhou XD, Liu L, Zhang Q. Enhancing content-based image retrieval by exploiting relevance feedback logs. Journal of Software, 2004,15(1):41~48. /1000-9825/15/41.htm Abstract: Relevance feedback (RF) has been successfully used in content-based image retrieval (CBIR). However, most CBIR systems seldom reuse the latent semantic correlation among images revealed by RF log to guide retrieving across sessions. In this paper, concurrence of images in a RF record is regarded as a kind of semantic homogeneity in certain context and the image-retrieving problem is cast as an authority-image-finding task. Records in RF logs first extend the result from traditional CBIR systems. This produces a relevant graph of images related to the query with multiplex contexts. Then, a modified HITS algorithm is applied to it to distill consensus about semantic relevance. As a result, both visual content and semantic relevance can be maintained in image retrieval and the efficiency is much improved compared with traditional CBIR methods. Experimental resu