CAPTCHA

With the expansion of Internet, a great many daily activities are now done through Internet for convenience, including communication, education and e-commerce. As a matter of fact, web sites must ensure that the services are supplied to legitimate human users rather than bots to prevent service abuse. Most of them ask users to challenge puzzles before they are authenticated to the service. The puzzles, which are first introduced by Luis von Ahn et al. in 2003, are CAPTCHAs.

CAPTCHA stands for Completely Automated Public Turing Test to Tell Computers and Human Apart, which is universally a secure measure to differentiate human users from bots and adopted by many websites. CAPTCHA is an automated Turing test that can generate and grade tests which human can easily pass while bots cannot. The existing CAPTCHAs can be generally classified into three categories: Text-based CAPTCHAs, Image-based CAPTCHAs and Sound-based CAPTCHAs. Text-based CAPTCHAs relay on the distortion of digits/letters and other visual effects added in the background image. The content can be a word or random alphanumeric characters. The user is asked to identify the distorted characters and entered them

Image-based CAPTCHAs ask users to enter proper labels which can describe the image properly or require users to  rotate the image to the correct direction. So the images and the corresponding labels which are not unique should be restored.