Translator Disclaimer
Paper
23 January 2017 Pornographic information of Internet views detection method based on the connected areas
Author Affiliations +
Proceedings Volume 10322, Seventh International Conference on Electronics and Information Engineering; 1032228 (2017) https://doi.org/10.1117/12.2265170
Event: Seventh International Conference on Electronics and Information Engineering, 2016, Nanjing, China
Abstract
Nowadays online porn video broadcasting and downloading is very popular. In view of the widespread phenomenon of Internet pornography, this paper proposed a new method of pornographic video detection based on connected areas. Firstly, decode the video into a serious of static images and detect skin color on the extracted key frames. If the area of skin color reaches a certain threshold, use the AdaBoost algorithm to detect the human face. Judge the connectivity of the human face and the large area of skin color to determine whether detect the sensitive area finally. The experimental results show that the method can effectively remove the non-pornographic videos contain human who wear less. This method can improve the efficiency and reduce the workload of detection.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Huibai Wang and Ajie Fan "Pornographic information of Internet views detection method based on the connected areas", Proc. SPIE 10322, Seventh International Conference on Electronics and Information Engineering, 1032228 (23 January 2017); https://doi.org/10.1117/12.2265170
PROCEEDINGS
6 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT


Back to Top