Publication Type:

Journal Article


International Journal of Pure and Applied Mathematics, Volume 117, Issue 10, p.31-35 (2017)



To ensure security of confidentiality maintained complex systems; biometrics has become the most efficient solution, which refers to the automatic identification of a person based on their physiological or behavioral characteristics. This paper proposes a Biometric Authentication system using deep learning concepts, where the finger knuckle of the user is considered to enhance the security of the system. This model can recognize an authorized user based on major finger knuckle pattern using Convolution Neural Network (CNN) and extracts the features and are optimally compared with the trained images. The CNN is trained by back propagation algorithm with stochastic gradient descent and minibatch learning with the help of Neural Network Toolbox in MATLAB, which can provide accurate output than any other algorithms used for authentication.

Cite this Research Publication

N. Lalithamani, “Finger Knuckle Biometric Authentication using Convolution Neural Network”, International Journal of Pure and Applied Mathematics, vol. 117, no. 10, pp. 31-35, 2017.