A Reading Oriented Overlapping Text based CAPTCHA

Abstract

CAPTCHA is a security technique used widely over the Internet to verify whether the end user is a human. Textbased CAPTCHAs are the most commonly used. The security of text-based CAPTCHA depends on the ability to resist the segmentation and recognition attacks. The Reading Oriented Overlapping Text (ROOT) based CAPTCHA, introduced in this article, consists of overlapping alphanumeric letters both hand written and computer generated along with a reading pattern scheme that helps to use the same CAPTCHA multiple number of times. The proposed ROOT based CAPTCHA generation algorithm is discussed along with its resistivity to known attacks.