A New Image Retrieval Algorithm in Digital Library
Yan Qinghong1,2 Peng Yuxing2
1(China Denfense Science and Technology Information Center, Beijing 100036,China) 2(PDL, National University of Defense Technology, Changsha 410073,China)
In this paper, a new image retrieval algorithm in digital library is proposed. It is based on the combination of visual features and semantic contents, in addition to giving a dynamic similarity metric eguation by relevance feedback technique. Experiments on our prototyping system showes that it can get higher retrieval rate than only by visual features.
闫庆红,彭宇行. 一种新的数字图书馆图像检索算法[J]. 现代图书情报技术, 2005, 21(12): 30-33.
Yan Qinghong,Peng Yuxing. A New Image Retrieval Algorithm in Digital Library. New Technology of Library and Information Service, 2005, 21(12): 30-33.
1Rui Y,Huang T S,Mehrotra S.Content-based image retrieval with relevance feedback in MARS.In:Proc IEEE International Conference on Image Proceeding,1997
2Vasconcelos N, Lippman A. Bayesian representations and learning mechanisms for content based image retrieval. In:Proc SPIE Storage and Retrieval for Media Databases.2000.43-54
3W.Y.Ma and B.S.Manjunath, Netra: A toolbox for Navigating Large Image Databases. In:Proc. IEEE Int. Conf. on Image Processing.1997
4Flickner M et al. Query by image and video content: The QBIC system. IEEE Computer,1995
5段立娟等图像检索中的动态相似性度量方法计算机学报,2001(11):1156-1162
6朱兴全等iFind:一个结合语义和视觉特征的图像相关反馈检索系统计算机学报,2002,25(7):681-688