FaceDCAPTCHA: Face Detection based Color Image CAPTCHA
With data theft and computer break-ins becoming increasingly common, there is a great need for secondary authentication means to reduce automated attacks while posing a minimal hindrance to legitimate users. CAPTCHA is one of the possible ways to classify human users and automated scripts. Though text-based CAPTCHAs are used in many applications, they pose a challenge due to language dependency. In this paper, we propose a face image-based CAPTCHA as a potential solution. To solve the CAPTCHA, users must correctly identify visually-distorted human faces embedded in a complex background without selecting any non-human faces. The proposed algorithm generates a CAPTCHA that offers better human accuracy and lower machine attack rates compared to existing approaches.
Competition Announcement
We would like to announce a competition to break FaceDCAPTCHA. In this competition, 500 FaceDCAPTCHAs along with annotations will be made available to the interested researchers. Research groups can develop algorithms to "break" the proposed CAPTCHA and send us the executable with clear instructions to run the executable. The executable will be evaluated on a set of 500 previously unseen FaceDCAPTCHAs that will not be available to the public (it will be available at a later stage - once the competition is closed). Top performing algorithms and the results will be listed on this website.If you are interested, please send a request email to gauravgs@iiitd.ac.in with subject: "FaceDCAPTCHA competition". Last date to send email for participation and submitting executable is December 31st, 2012.