Classification of violent web images using context based analysis
Radhouane Guermazi, Mohamed Hammami, Abdelmajid Ben Hamadou · 2010
The development of the Web has been paralleled by the proliferation of a harmful content on its pages. Using Violent Web images as a case study, we tend to present a novel approach to their classification. This subject is of high importance as it has a potential use in many applications such as violent Web sites filtering. We, therefore, focus our attention on the extraction of contextual image features from the Web page. Also, we present a comparative study of different data mining techniques to classify violent Web images. The results we achieved show that our approach can detect violent content effectively.