Human Interactive Proofs (HIPs) are automatic reverse Turing tests designedto distinguish between various groups of users. Completely Automatic PublicTuring test to tell Computers and Humans Apart (CAPTCHA) is a HIP system thatdistinguish between humans and malicious computer programs. Many CAPTCHAs havebeen proposed in the literature that text-graphical based, audio-based,puzzle-based and mathematical questions-based. The design and implementation ofCAPTCHAs fall in the realm of Artificial Intelligence. We aim to utilizeCAPTCHAs as a tool to improve the security of Internet based applications. Inthis paper we present a framework for a text-based CAPTCHA based on Devanagariscript which can exploit the difference in the reading proficiency betweenhumans and computer programs. Our selection of Devanagari script-based CAPTCHAis based on the fact that it is used by a large number of Indian languagesincluding Hindi which is the third most spoken language. There is potential foran exponential rise in the applications that are likely to be developed in thatscript thereby making it easy to secure Indian language based applications.
展开▼
