Classifying offensive sites based on image content

Combining Classifiers for Web Violent Content Detection and Filtering

“…(b) Intelligent content Web filtering which falls in the general problem of automatic website categorization and uses machine learning. At least, three categories of intelligent content Web filtering can be distinguished : (i) textual content Web filtering [1], (ii) structural content Web filtering [2], [3] and (iii) Visual content Web filtering [4]. Other Web filtering solutions are based on an analysis of textual, structural and visual contents, of a Web page [5].…”

“…To evaluate our violent Web filtering tool, we carry out an experiment which compares, on the test data set , "WebAngels filter" with four litigious content detection and filtering systems, knowing, control kids 2 , content protect 3 , k9-webprotection 4 and Cyber patrol 5 . these tools were been parametric to filter violent Web Content.…”

Smart Content Recognition from Images Using a Mixture of Convolutional Neural Networks

“…The structure of a group of skin color regions is analyzed to see how they are connected. Several methods have been proposed to detect the shape features such as contour-based features [1] where the outlines of the skin region are extracted and used as a feature, Hu and Zernike moments of the skin distribution [13], and Geometric constraints which model the human body geometry [2].…”

“…This method classifies a region of pixels as either skin or non-skin. The skin color can be detected manually using a color range [1], computed color histograms [4], or parametric color distribution functions [3]. Once a skin color model of the image has been defined, the adult image can be detected by a simple skin color histogram threshold, or by passing the statistics of the skin information to a classifier [11].…”

“…Another blocking method uses image filtering [1,9,11]. This method works directly on the images, trying to detect if the image contains adult content.…”