Proposal of Jawi CAPTCHA Using Digraphia Feature of the Malay Language

Abstract

This paper proposes a new text-based CAPTCHA using Jawi script and Latin script, which are both used in the Malay language writing system. Many web sites have adopted CAPTCHA to prevent bots and other automated programs from malicious activities such as posting comment spam. Text-based CAPTCHA is the most common and earliest CAPTCHA. But as optical character recognition (OCR) technology has improved, the intensity of distortions that must be applied to a CAPTCHA for it to remain unrecognizable by OCR has increased. This has reached a point where humans are having difficulty recognizing CAPTCHA text. The idea of the proposed CAPTCHA is to generate two identical character strings, one written in Latin script and the other in Jawi script. Because some of the strings characters are hidden by obstacles, users need to combine both strings to solve this CAPTCHA. This idea uses the fact that most Jawi characters have one-to-one correspondence with Latin characters. A series of experiments was carried out to evaluated the performance of the proposed CAPTCHA. First, a computer program was developed with various software languages for the usability evaluation. The results showed that the average time to solve the CAPTCHA and the accuracy rates were acceptable compared with the indices reported in existing research. Next, two OCR programs were applied to the Jawi CAPTCHA, and it was demonstrated that they could not read the partially hidden Latin and Jawi strings. Lastly, we discussed the effectiveness of the proposed CAPTCHA by relating to the priming effect.