Abstract: A CAPTCHA (an acronym for "Completely Automated Public Turing test to tell Computers and Humans Apart") is a type of challenge-response test used in computing to determine whether or not the user is human. Most existing CAPTCHAs are text-based. The user is presented with visually distorted text and asked to type it in correctly to prove he or she is a human and not a computer. Due to recent developments in technology, users are rapidly adopting smartphones, tablets, and other non-traditional smart computing devices in lieu of desktop and laptop computers. Many mobile devices lack a physical keyboard, which makes text-based input cumbersome and error-pron. Further, most text based CAPTCHAs are (English) language-dependent and not suitable for multilingual worldwide usage. Some researchers have proposed alternatives to character recognition, in the form of image recognition CAPTCHAs which require users to identify simple objects in the images presented. The unique touch screen technology of mobile devices can be leveraged to create an additional layer of security that is both effective and user-friendly. Fg CAPTCHA proposes a novel image-based CAPTCHA that combines the touch-based input methods favoured by mobile devices with genetically optimized face detection tests to provide a solution that is simple for humans to solve, ready for worldwide use, and provides a high level of security by being resilient to automated computer attacks. It provides a set of embedded images, some of which are photographs of real human faces and others which are cartoons, sketches, or photos of animals representing face-like images to make correctly detecting human faces challenging for computers, complex background pattern designed to confuse the automatic face detection software, thereby increasing the false positive detection rate and a set of visual distortion types (e.g., blurring, contrast adjustment) and the amount of distortion to apply. The proposed genetically optimized fg CAPTCHA works efficiently on both touch screens used by tablets and smartphones and on traditional computers, achieving a high 88% human accuracy rate during evaluation. It does so without compromising performance, offering an effective 0% automated attack rate.
Keywords: fgcaptcha, existing captcha, newly added features in fgcaptcha , advantages of fg captcha.