BREAKING A VISUAL CAPTCHA : A NOVEL APPROACH USING HMM

Completely Automated Public Turing Tests to Tell Computers and Humans Apart (CAPTCHAs) are the automatic filters that are widely used these days to disallow any automated script that can perform the work of a human. CAPTCHAs are built in such a way that it is very difficult for any automated script to break them. In this paper, a novel approach for EZ-Gimpy CAPTCHAs has been proposed that first preprocesses the given CAPTCHA, segments its characters, matches the character’s features with the features in a characteristic table and then uses HMM to recognize the characters of the CAPTCHA. Results verify the effectiveness of the approach.