Image retrieval using long-term semantic learning

被引：6
作者：
Cord, Matthieu [1 ]
Gosselin, Philippe H. [1 ]
机构：
[1] CNRS, UMR 8051, ETIS, 6,Ave Ponceau, F-95014 Cergy Pontoise, France
来源：
2006 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP 2006, PROCEEDINGS | 2006年
关键词：
image classification; image databases; learning systems; information retrieval;
D O I：
10.1109/ICIP.2006.313127
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The automatic computation of features for content-based image retrieval still has difficulties to represent the concepts the user has in mind. Whenever an additional learning strategy (such as relevance feedback) can improve the results of the search, the system performances still depend on the representation of the image collection. We introduce in this paper a supervised optimization of a set of feature vectors. According to an incomplete set of partial labels, the method improves the representation of the image collection, even if the size, the number, and the structure of the concepts are unknown. Experiments have been carried out on a large general database in order to validate our approach.
引用
收藏
页码：2909 / +
页数：3
相关论文
共 14 条
[1]   Improving support vector machine classifiers by modifying kernel functions [J].
Amari, S ;
Wu, S .
NEURAL NETWORKS, 1999, 12 (06) :783-789
[2]  
CHANG E, 2003, IEEE INT C IM PROC B
[3]  
Cristianmi N., 2001, NEURAL INFORM PROCES
[4]  
FOURNIER J, 2002, INT C IM PROC ICIP R
[5]  
GOSSELIN PH, 2004, IEEE INT C IM PROC S
[6]  
GOSSELIN PH, 2005, IEEE INT C IM PROC G
[7]  
HAN J, 2003, IEEE INT C IM PROC B
[8]  
Heisterkamp DR, 2002, INT C PATT RECOG, P134, DOI 10.1109/ICPR.2002.1047417
[9]  
HEISTERKAMP DR, 2001, INT C COMP VIS PATT
[10]  
Lanckriet G.R.G., 2002, INT C MACH LEARN SYD
12