Abstract
Detection model of knotty illicit image is designed to detect special erotic image, such as nude chat image and advertising prostitution image, which are difficulty identified by conventional algorithm. Text information and skin-color information are detected in the image detection windows set according to the characteristic of images. Experimental results demonstrate that the model can obtain good results in detecting special erotic image.
Publisher
Trans Tech Publications, Ltd.
Reference7 articles.
1. I. Mofakharul, W. Paul, Y. John, H. Mazher, A. S. Lubaba. Illicit Image Detection Using Erotic Pose Estimation Based on Kinematic Constraints, Innovations and Advances in Computer, Information, Systems Sciences, and Engineering Lecture Notes in Electrical Engineering, Volume 152, 2013, 481-495.
2. P. Y. Ni, J. Huang. Pornographic Image Filtering Method Based on Human Key Parts. Proceedings of the 2012 International Conference on Information Technology and Software Engineering Lecture Notes in Electrical Engineering, Volume 212, 2013, 677-688.
3. K. M. Liang, S. D. Scott, M. Wagas. Detecting pornographic images. In: Asian Conference on Computer Vision, 2004, 497-502.
4. W. Wei. The Research on Network Pornographic Image Filtering Based on Erotogenic-part Detection[D]. Jilin: Jilin University, (2008).
5. B. Lu, Y. W. Gong, J. L. Yao, etc. Pornographic image filtering method based on erotogenic-zone detection [J]. Computer Applications and Software, 2011, 28(4): 154-158.