Automatic Web Rating: Filtering Obscene Content on the Web

We present a method to detect automatically pornographic content on the Web. Our method combines techniques from language engineering and image analysis within a machine-learning framework. Experimental results show that it achieves nearly perfect performance on a set of hard cases.

• Type: Conference
• Year: 2000
• Where: ERCIMDL
• Authors: Konstantinos Chandrinos, Ion Androutsopoulos, Georgios Paliouras, Constantine D. Spyropoulos
• Keywords: Education, ERCIMDL 2000, Machine-learning Framework, Method Combines Techniques, Pornographic Content