Manisha B. Thombare, Parigha M. Derle, Arpita K. Wandre
Download PDFCompletely Automated Public Turing Tests to Tell Computers and Humans Apart (CAPTCHAs) are now an almost standard security mechanism for defending against undesirable and malicious bot programs on the Internet. CAPTCHAs generate and grade tests that most humans can pass but current computer programs can't. Such tests are based on hard, open artificial intelligence problems. This paper presents a method that splits the CAPTCHA image into several parts with rotation and draws random lines and circles to the background, along with a grid effect, so that OCR programs are confused while distinguishing characters, while remaining readable to humans.
CAPTCHA, Internet security, Usability
