FR-CAPTCHA: CAPTCHA Based on Recognizing Human Faces

• DOI: 10.1371/journal.pone.0091708
• Publication Date: 2014-04-15T16:33:45Z
• Authors: Gaurav Goswami; Brian M. Powell; Mayank Vatsa; Richa Singh; Afzel Noore
• Keywords: CAPTCHA; Turing test; Turing

A Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) is designed distinguish humans from machines. Most of the existing tests require reading distorted text embedded in a background image. However, many CAPTCHAs are either too difficult for due excessive distortions or trivial automated algorithms solve. These also suffer inherent language as well alphabet dependencies not equally convenient people different demographics. Therefore, there need devise other which can mitigate these challenges. One such matching two faces establish if they belong same individual not. Utilizing face recognition test, we propose FR-CAPTCHA based on finding pairs human an We observe that, compared implementations, achieves accuracy 94% robust against attacks.