Palmprint verification based on 2D - Gabor wavelet and pulse-coupled neural network

To alleviate the limitation that the recent texture based algorithms for palmprint recognition yield unsatisfactory robustness to the variations of orientation, position and illumination in capturing palmprint images, this paper describes a novel texture based algorithm for palmprint recognition combining 2D Gabor wavelets and pulse coupled neural network (PCNN). In the proposed algorithm, palmprint images are decomposed by 2D Gabor wavelets, and then PCNN is employed to imitate the creatural vision perceptive process and decompose each Gabor subband into a series of binary images. Entropies for these binary images are calculated and regarded as features. A support vector machine-based classifier is employed to implement classification. Experimental results show that the proposed approach yields a better performance in terms of the correct classification percentages and relatively high robustness to the variations of orientation, position and illumination compared with the recent texture based approaches.