Adult video content detection using Machine Learning Techniques

Abstract

Automatic adult video detection is a problem of interest for many organizations around the globe aiming to restrict the availability of potentially harmful material for young audiences. Being most of the existing techniques a mere extension of the image categorization problem. In the present work we employ video genre classification techniques applied specifically for adult content detection by considering cinematic principles. Shot structure and camera motion in the temporal domain are used as the main features while skin detection and color histograms representation in the spatial domain are utilized as complementary features. Using a data set of more than 7 hours of video, our experiments comparing two different SVM algorithms achieve a high accuracy of 94.44%.