Joint detection method of pornographic images with skin-like color background
A novel approach is proposed to automatically detect pomographic images with skin-like color background on the Intemet using the locations of human faces and bodies. It has two separate skin-color detection steps: the first one is to quickly detect the potential human skin-color regions; and the sec...
Saved in:
Published in | 高技术通讯(英文版) Vol. 18; no. 2; pp. 132 - 138 |
---|---|
Main Author | |
Format | Journal Article |
Language | English |
Published |
College of Communication Engineering, Chongqing University, Chongqing 400044, P.R.China%Chongqing College of Electronic Engineering, Chongqing, 401331, P.R.China%High Performance Network Laboratory, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, P.R.China
01.06.2012
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | A novel approach is proposed to automatically detect pomographic images with skin-like color background on the Intemet using the locations of human faces and bodies. It has two separate skin-color detection steps: the first one is to quickly detect the potential human skin-color regions; and the second one is to use an off-the-shelf face detector to locate a human face and then apply hypothesis testing based on series of assumptions which take into account the face-height ratio, body orientation and modem photograph composition common sense, etc. After that, a template matching method is used to further discriminate normal images or pornographic ones. Experimental results show that the proposed method has high precision and real time speed. |
---|---|
Bibliography: | Tang Chaowei, Leng Zhenfeng ,Shao Yanqing ,,Tang Hui,Zhou Xu(* College of Communication Engineering, Chongqing University, Chongqing 400044, P. R. China) (** Chongqing College of Electronic Engineering, Chongqing, 401331, P. R. China) (*** High Performance Network Laboratory, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, P. R. China) face detection, pornographic image, skin-like color background, skin-color detection, template matching A novel approach is proposed to automatically detect pomographic images with skin-like color background on the Intemet using the locations of human faces and bodies. It has two separate skin-color detection steps: the first one is to quickly detect the potential human skin-color regions; and the second one is to use an off-the-shelf face detector to locate a human face and then apply hypothesis testing based on series of assumptions which take into account the face-height ratio, body orientation and modem photograph composition common sense, etc. After that, a template matching method is used to further discriminate normal images or pornographic ones. Experimental results show that the proposed method has high precision and real time speed. 11-3683/N |
ISSN: | 1006-6748 |
DOI: | 10.3772/j.issn.1006-6748.2012.02.005 |