Relevance feedback based on parameter estimation of target distribution

被引:3
作者
Sia, KC [1 ]
King, I [1 ]
机构
[1] Chinese Univ Hong Kong, Dept Comp Sci & Engn, Shatin, Hong Kong, Peoples R China
来源
PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3 | 2002年
关键词
CBIR; parameter estimation; expectation maximization; relevance feedback;
D O I
10.1109/IJCNN.2002.1007822
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Relevance Feedback formulations have been proposed to refine query result in Content-Based Image Retrieval (CBIR) in the past few years. Many of them focus on a learning approach to solve the feedback problem. In this paper, we present an Expectation Maximization (EM) approach to estimate the user's target distribution through user's feedback. Furthermore, we describe how to use Maximum Entropy display to fully utilize user's feedback information. We detail the process and also demonstrate the result through experiments.
引用
收藏
页码:1974 / 1979
页数:2
相关论文
共 8 条
[1]   The Bayesian image retrieval system, PicHunter:: Theory, implementation, and psychophysical experiments [J].
Cox, IJ ;
Miller, ML ;
Minka, TP ;
Papathomas, TV ;
Yianilos, PN .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2000, 9 (01) :20-37
[2]   MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].
DEMPSTER, AP ;
LAIRD, NM ;
RUBIN, DB .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38
[3]  
King I, 2001, 8TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING, VOLS 1-3, PROCEEDING, P699
[4]   Text classification from labeled and unlabeled documents using EM [J].
Nigam, K ;
McCallum, AK ;
Thrun, S ;
Mitchell, T .
MACHINE LEARNING, 2000, 39 (2-3) :103-134
[5]   Relevance feedback: A power tool for interactive content-based image retrieval [J].
Rui, Y ;
Huang, TS ;
Ortega, M ;
Mehrotra, S .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 1998, 8 (05) :644-655
[6]  
Tian Q, 2000, 2000 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, PROCEEDINGS VOLS I-III, P1199, DOI 10.1109/ICME.2000.871576
[7]  
WANG T, 2001, IEEE COMP SOC C COMP
[8]  
Wu Y, 2000, PROC CVPR IEEE, P222, DOI 10.1109/CVPR.2000.855823