Finger Vein Presentation Attack Detection using Block-wise Variance-based Image Quality Assessment

Biometrics refer to the physiological and behavioural characteristics uniquely possessed by individuals. Physiological biometrics are characteristics that can be measured from the human body such as palm print, fingerprint, iris, and finger vein. Meanwhile behavioural biometrics are measurement of patterns of humans such as gait, signature, and gesture. Among the different biometrics in use today, finger vein biometrics have been gaining popularity and are widely used for user authentication especially in the financial and access control application. Unfortunately, there are attack attempts known as presentation attack to bypass the system by presenting fake finger vein images with the aim to spoof the finger vein sensor or reader. This research aims to introduce an image quality assessment approach namely Block-wise Variance-based Image Quality Assessment (BV-IQA) that evaluates the discrimination of noisiness and blurriness information in the finger vein images for presentation attack detection. Experiments on two benchmark datasets, SCUT and VERA validated the proposed method's effectiveness, yielding a promising result of 0.14% ACER.