Exploring dorsal finger vein pattern for robust person recognition

Abstract

Finger vein based biometric recognition has increasingly generated interest amongst biometric researchers because of the accuracy, robustness and anti-spoofing propertie. Prior efforts the are documented in the finger vein biometrics literature have only investigated the ventral vein pattern that is formed on the lower part of the finger underneath the skin surface. This paper investigates a new finger vein biometric approach by exploring the vein pattern that is present in the dorsal finger region. Thus, the dorsal finger vein pattern can be used as an independent biometric characteristic useful for the recognition of the target subject. We presented a complete automated approach with the key steps of image capturing, Region of Interest (ROI) extraction, pre-processing to enhance the vein pattern, feature extraction and comparison. This paper also introduces a new database of dorsal finger vein patterns from 125 subjects that resulted in 500 unique fingers with 10 samples each that results in a total of 5000 dorsal finger vein samples. Extensive experiments carried out on our new dorsal finger vein database achieve promising accuracy and thereby provide new insights on this new biometric approach.