Skin detection for adult image identification
Jung-Jae Yu, Seung-Wan Han · 2014
This work is aimed at the estimation of the skin region in pornographic images to identify and block the pornographic contents. We propose a novel method to estimate the skin region using simple operation in HSV color space and additional postprocessing to reduce the noise effects. Our method does not require any pre-process such as object detection. It is fast and its result is good enough to be used for fitlering out the clear non-objectionable images before main identification process. So the proposed method can be used as pre-processing for more accurate poronographic image identification process.