A Novel Approach for Region-of-Interest Detection in Pornographic Images

Region-of-interest (ROI) detection plays an important role in filtering out pornographic images. Skin-color models, as a traditional approach, extract skin-color regions as ROI. However, the approach is difficult to differentiate between human skins and other objects with the skin-color. Furthermore, skin-color regions are always larger than the subareas containing pornographic parts. In this paper, we present a novel approach for ROI detection in pornographic images by integrating visual attention and skin-color models. A novel saliency map model is firstly constructed. Then it is integrated with a skin-color model and a face detection model to capture ROI. Experimental results show that our approach is more precisely than using the skin-color model alone. 3rd International Conference on Multimedia Technology(ICMT 2013) © 2013. The authors Published by Atlantis Press 861