RF*IPF: A weighting scheme for multimedia information retrieval

被引:2
作者
Wang, JZ [1 ]
Du, YP [1 ]
机构
[1] Penn State Univ, Sch Informat Sci & Technol, University Pk, PA 16802 USA
来源
11TH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, PROCEEDINGS | 2001年
关键词
D O I
10.1109/ICIAP.2001.957039
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Region-based approach has become a popular research trend in the field of multimedia database retrieval. In this paper we present the Region Frequency and Inverse Picture Frequency, (RF*IPF) weighting, a measure developed to unify, region-based multimedia retrieval systems with text-based information retrieval systems. The weighting measure gives the highest weight to regions that occur often in a small number of images in the database. These regions are considered discriminators. With this weighting measure, we can blend image retrieval techniques with TF*IDF-based text retrieval techniques for large-scale Web applications. The RF*IPF weighting has been implemented as a part of our experimental SIMPLIcity image retrieval system and tested on a database of about 200,000 general-purpose images. Experiments have shown that this technique is effective in discriminating images of different semantics. Additionally, the overall similarity approach enables a simple querying interface for multimedia information retrieval systems,
引用
收藏
页码:380 / 385
页数:6
相关论文
共 25 条
[1]  
[Anonymous], 1997, P ARPA IMAGE UNDERST
[2]  
CARSON C, 1999, P INT C VIS INF SYST
[3]  
Daubechies I, 1992, 10 LECT WAVELETS
[4]  
Faloutsos C., 1994, Journal of Intelligent Information Systems: Integrating Artificial Intelligence and Database Technologies, V3, P231, DOI 10.1007/BF00962238
[5]   Visual information retrieval [J].
Gupta, A ;
Jain, R .
COMMUNICATIONS OF THE ACM, 1997, 40 (05) :70-79
[6]  
Hartigan J. A., 1979, Applied Statistics, V28, P100, DOI 10.2307/2346830
[7]  
Jia Li, 2000, Proceedings ACM Multimedia 2000, P147
[8]   Is there any texture in the image? [J].
Karu, K ;
Jain, AK ;
Bolle, RM .
PATTERN RECOGNITION, 1996, 29 (09) :1437-1446
[9]   Multiresolution image classification by hierarchical modeling with two-dimensional hidden Markov models [J].
Li, J ;
Gray, RM ;
Olshen, RA .
IEEE TRANSACTIONS ON INFORMATION THEORY, 2000, 46 (05) :1826-1841
[10]   Context-based multiscale classification of document images using wavelet coefficient distributions [J].
Li, J ;
Gray, RM .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2000, 9 (09) :1604-1616