Palm Vein Based Authentication System by Using Convolution Neural Network

The recognition of hand palm print through veins is one of the promising biometric techniques, which has received great interest lately due to its accuracy in identifying individuals. Although the literature witnessed several techniques and developments to deal with the problem of identifying people through the veins in the palm, the technology is still in its infancy. In this research, we propose our palm print recognition model which use convolution neural networks preceded by the pre-processing stages to optimise the data and to extract the important regions. The pre-processing helped in extracting the vein pattern which feed into the proposed convolution neural network model. The CASIA database has been used; it contains 7200 images taken form 100 people based on 6 wavelengths (940 nm, 850 nm, 700 nm, 630 nm, 460 nm, and white). The model has been tested with all wavelengths in the database. AlexNet is used for benchmarking. The results show that our approach using the proposed pre-processing has helped to surpass AlexNet in terms of performance, speed, and accuracy.