Faster and Better: A Deep Learning Approach to Finger Vein Authentication

Abstract

In the present era of electronic development in the world it is sensibly challenging to secure the personal information. Considering the constraint of the uni-modal biometrics authentication the appropriate selection of modality plays vital role for authentication. This paper discusses about a topical authentication system using finger vein. The performance of identification process may degrade due to these factors and implies the need of defining Region of Interest (ROI).  In this paper, the extraction of features of finger vein based on deep learning technique is proposed, RROI localization which proves to be much effective and forcefulness. Two types of errors false acceptance rate (FAR) and false rejection rate(FRR) is discussed in this paper.