Footprint biometric authentication using SqueezeNet

Abstract

Biometric authentication is a process of identity verification once an identity is claimed by an individual. It uses unique features on the human body. Footprints are a new biometric feature that has sparked interest among researchers, as this feature is universal, easy to extract and has not changed throughout time. The focus of researchers in this field is to improve the recognition rate. Various techniques have been developed for this purpose, but the accuracy percentage is at 98% with an equal error rate (EER) of 6.1%. This paper proposes the use of a new technique called SqueezeNet in classifying footprint images. SqueezeNet belongs to the convolutional neural network (CNN) family. In this study, 300 footprint images were used from 15 individuals. The 70% of these images were used to train the proposed SqueezeNet network, while the rest were used for testing. At the end of this simulation, SqueezeNet has achieved an accuracy of 98.67% with an EER of 2.1%.