InfoPrint: A View of Retrieval Results for Image Retrieval System
暂无分享,去创建一个
In this paper, we propose a novel view of retrieval results for image retrieval systems. Generally, many image retrieval systems output retrieval results as ranked lists by the order of retrieval status values (RSVs) of the images. However, users cannot find how the images are relevant, from these RSVs in the ranked lists. Because, the distributions of RSVs are depended on the retrieval systems. In this paper, we propose a conversion method from RSV to InfoPrint, a small image which is generated by the RSV. Using Info-Print, users can intuitively find which retrieval targets are relevant to the users.
[1] Heinz-Otto Peitgen,et al. The beauty of fractals - images of complex dynamical systems , 1986 .
[2] Hans-Peter Kriegel,et al. State-of-the-Art in Content-Based Image and Video Retrieval , 2001, Computational Imaging and Vision.
[3] Jian-Gang Zhu,et al. Noise Characteristics of Interacting Transitions in Longitudinal Thin Film Media , 1994, Digest of the Magnetic Recording Conference.
[4] S. W. Yuan,et al. Statistical data analysis of magnetic recording noise mechanisms , 1992 .