SKIN DETECTION IN PORNOGRAPHIC VIDEOS USING THRESHOLD TECHNIQUE
Sanaa El Fkihi, Driss Aboutajdine · 2012
Adult classification of images and videos is one of the major tasks for semantic analysis of visual co ntent. A modern approach to this problem is introducing a mechanism to prevent objectionable access to this t ype of content. In this paper, we propose a real-time s ystem that can classify input videos into adult or non-adult videos. First, videos were filtered by skin color m odel using threshold technique. Then, the output vi deos are classified by neural network for taken the deci sion. We notice that the detection of an adult vide o is based on the detection of the adult images that com pose the considered video. The simulation shows tha t this system achieved 90% of the true rate.