Human authentication process using finger knuckle surface with artificial Neural Networks based on a hybrid feature selection method

An improved human authentication process using knuckle surface for personal identification has shown promising results. The texture pattern produced by the finger knuckle bending is highly unique and makes the surface a distinctive biometric identifier. In this paper we proposed a new approach for efficient and more secure personal identification using knuckle surface. A specific data acquisition device is constructed to capture the finger knuckle surface images, and then an efficient finger knuckle print algorithm is presented with trained neural network. The finger back surface images from each of the users are normalized to minimize the scale, translation and rotational variations in the knuckle images. The main attraction of this proposed method is that a hybrid feature selection method of Lempel-Ziv Feature Selection and Principle Component Analysis is used for feature extraction and an artificial Neural Network based on Scaled Conjugate Gradient is used for the recognition. The experimental results from the proposed approach are promising and confirm. Compared with the other existing finger-back surface based biometric systems, the proposed system is more efficient and can achieve higher recognition rate in real time.