IDENTIFY BIOMETRIC CAPTCHA BY USING BACK-PROPAGATION TECHNIQUE OF ARTIFICIAL NEURAL NETWORK

CAPTCHA (Completely Automated Public Turing Test to tell computers and humans apart) is a very successful and latest technology for security purposes. In this paper, we describe another form of CAPTCHA called biometric CAPTCHA. We have seen biometric CAPTCHA almost every place of security. This paper focuses another mechanism for the storage of Biometric CAPTCHA using the technique of Artificial Neural Networks. We proposed Fingerprint recognition system of Biometric CAPTCHA. In this paper, we have taken the image of thumb impression of individual. Image is converted into binary bits by using online converter (image to binary converter). After that based on these binary bits we educate the network. Additionally, recalling is also done at the end of the research work. The performance curve shows that only 6 iteration is required to train the network and only 18 iteration is required to recall the network. We get satisfied result according to learning and recalling curve. MATLAB 2017 software is used for simulation work. The experiment results prove that the new model has a good recognition effect of biometric CAPTCHA when trained using Back-Propagation Algorithm