Low complexity iris recognition based on wavelet probabilistic neural networks

In this paper, a new technique is proposed for high efficiency iris recognition, which adopts Sobel transform and vertical projection to extract iris texture feature and wavelet probabilistic neural network (WPNN) as iris biometric classifier. The WPNN combines wavelet neural network and probabilistic neural network for a new classifier model which will be able to improve the biometrics recognition accuracy as well as the global system performance. A simple and fast training algorithm, particle swarm optimization (PSO), is also introduced for training the wavelet probabilistic neural network. In iris matching, the CASIA iris database is used and the experimental results show that the feasibility and performance of the proposed method.