An erotic image recognition algorithm based on trunk model and SVM classification

被引:0
作者
Sun, Qindong [1 ]
Huang, Xinbo
Guan, Xiaohong
Gao, Peng
机构
[1] Xian Univ Engn Sci & Technol, Sch Electromech Engn, Xian 710048, Shaanxi, Peoples R China
[2] Xian Univ Technol, Sch Engn & Comp Sci, Xian 710048, Shannxi, Peoples R China
[3] Xi An Jiao Tong Univ, Sch Elect & Informat Engn, Xian 710049, Peoples R China
来源
ADVANCES IN NEURAL NETWORKS - ISNN 2006, PT 3, PROCEEDINGS | 2006年 / 3973卷
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The characteristics of erotic images are analyzed in this paper and a novel algorithm for erotic images recognition is proposed. The algorithm first obtains the mask images of the recognized image by skin color detecting and texture analyzing, and then locates the possible position of human trunk in mask image according to the established model of trunk, based on which the characteristics of erotic images are extracted. Furthermore, the SVM classifier is used to recognize the erotic images based on those extracted characteristics. The experimental results show that the recognition accuracy rate of the proposed algorithm is higher than other algorithms and the proposed algorithm is efficient and effective.
引用
收藏
页码:346 / 351
页数:6
相关论文
共 9 条
[1]  
Brand J, 2000, INT C PATT RECOG, P1056, DOI 10.1109/ICPR.2000.905653
[2]  
DORAI C, 2000, P COMP VIS PATT REC, P13
[3]  
Duan Lijuan, 2002, Journal of Computer Aided Design & Computer Graphics, V14, P404
[4]  
Fan Xiao, 2004, Journal of Jilin University (Information Science Edition), V22, P631
[5]  
FLECK MM, 1996, P 4 EUR C COMP VIS C, P591
[6]   Training support vector machines: an application to face detection [J].
Osuna, E ;
Freund, R ;
Girosi, F .
1997 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1997, :130-136
[7]  
Platt J., 1998, MICROSOFT RES
[8]  
SCHWERDT K, 2000, P 4 IEEE INT C AUT F
[9]  
Vapnik V, 1999, NATURE STAT LEARNING