Infrared imaging of hand vein patterns for biometric purposes

TLDR

The study evaluates a novel non‑invasive imaging technique for hand vein patterns to serve as a biometric. The authors compare far‑infrared thermography and near‑infrared imaging, acquiring data from the back of the hand, palm, and wrist, and test both modalities in a preliminary biometric system. FIR thermography captures only large veins on the back of the hand and is sensitive to ambient conditions, whereas NIR imaging yields high‑quality images across all hand regions but can be corrupted by skin features; nevertheless, both modalities achieved 100 % identification accuracy in the preliminary biometric test.

Abstract

A novel non-invasive imaging technique to image the vein patterns in various parts of the hand for biometric purposes is evaluated. Two imaging methods are investigated: far-infrared (FIR) thermography and near-infrared (NIR) imaging. Experiments involving data acquisition from various parts of the hand, including the back of the hand, palm and wrist, were carried out using both imaging techniques. Analysis of the data collected shows that FIR thermography is less successful at capturing veins in the palm and wrist. FIR thermography can capture the large veins in the back of the hand, but it is sensitive to ambient temperature and humidity conditions as well as human body temperature. NIR imaging produces good quality images when capturing veins in the back of the hand, palm and wrist. NIR imaging is also more tolerant to changes in the environment and body condition but faces the problem of pattern corruption because of visible skin features being mistaken for veins. This corruption is not present in FIR imaging. An initial biometric system is investigated to test both FIR and NIR images for biometric purposes. The results show all the subjects were correctly identified, which indicates vein pattern biometrics with infrared imaging is a potentially useful biometric.