A contactless palm veins biometric system based on convolutional neural network

Alrahawe, E. A. M.; Humbe, V. T.; Shinde, G. N.

Personal recognition systems have emerged as highly important in the information society. Biometric systems are widely used because its reliability in distinguishing between the subjects. Contactless biometric systems are more important because of their advantages, especially, recently, during the current pandemic of COVID19 as they can be used to avoid the spread of such viruses. The use of hidden biometric traits is more secure, which makes the trait unable to stolen or duplicated, especially if the recognition in the live-ness process. Convolutional neural networks (ConvNet) have also gained a great success in large-scale image. Especially, in case of use the transfer learning techniques. In this study, we try to produce a contactless biometric system based on palm veins and use of Tungji large-scale contactless dataset to implement the system. This paper, divided into seven sections, starts with the general introduction;an overview on the related work and techniques used are in the second section;the third section about motivations and contribution of this work;the methodologies and dataset description the forth section;the proposed work and its results with implementation steps in the fifth section;continually to the comparison the current proposed system with the available in the literature in the section six, then the conclusion figured out in the last section. © 2021 IEEE.