A CAPTCHA is a challenge designed to distinguish humans from computer programs (’bots’) on the internet. To be useful, a CAPTCHA must be easily solved by most humans, while being difficult to solve by computer programs. Many people have seen examples of CAPTCHAs when signing up for a free webservice. They are typically implemented as a string of distorted text that must be transcribed.

My MS thesis explored the viability of a Video CAPTCHA.  In my Video CAPTCHA, users must provide three tags that best describe a video. These tags are then matched against an automatically generated list of ground-truth tags. A good starting place to learn more is our SOUPS ‘09 paper. For a live demo, please click here.

Related Publications

Related Talks

Related Links