Pornographic information of Internet views detection method based on the connected areas

Huibai Wang; Ajie Fan

doi:10.1117/12.2265170

23 January 2017 Pornographic information of Internet views detection method based on the connected areas

Huibai Wang, Ajie Fan

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.

Citation Download Citation

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

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available