Title :
Combining multiple SVM classifiers for adult image recognition
Author :
Zhao, Zhicheng ; Cai, Anni
Author_Institution :
Multimedia Commun. & Pattern Recognition Labs., Beijing Univ. of Posts & Telecommun., Beijing, China
Abstract :
Pornographic image recognition and filtering are of great significance for web security and content monitoring. In this paper, an adult image recognition method based on support vector machine (SVM) and erotic category is proposed. Global color and texture features and local SIFT feature are extracted to train multiple SVM classifiers for different erotic classes. Face detection is used to filter out normal close-up images. Four later fusion schemes are presented to determine the final result. A large scale test on 50,000 web images shows the proposed algorithm achieves 12.32% false positive rate(/p) and 14.17% false negatives rate(/h), which is better than five existing methods.
Keywords :
Internet; face recognition; feature extraction; image retrieval; image texture; support vector machines; adult image recognition; close-up images; content monitoring; face detection; image filtering; multiple SVM classifiers; pornographic image recognition; support vector machine; texture features; web images; web security; Classification algorithms; Face detection; Feature extraction; Image color analysis; Image recognition; Skin; Support vector machines; SIFT; SVM; face detection; object; pornographic image recognition;
Conference_Titel :
Network Infrastructure and Digital Content, 2010 2nd IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-6851-5
DOI :
10.1109/ICNIDC.2010.5657916