Finger-Vein Biometric Recognition: A Review

Finger-vein-based biometric technology has received wide attention and has made some positive achievements in improving the performance of personal identification. This article intends to provide an overview on the existing finger-vein-based biometric methods from the four steps of finger-vein recognition methods, including image acquisition, image preprocessing, feature extraction, and matching. After brief introduction of image acquisition and preprocessing, the applications of feature extraction method are summarized as: template-based method, representation-based method, and learning-based method. Moreover, deep-learning-based methods have been analyzed and discussed. To review and summarize these methods, the case studies of the finger-vein database are introduced to verify their effectiveness. Meanwhile, this article discussed the challenges and prospects of finger-vein recognition research, especially the 3-D finger-vein recognition research, to guide the future research direction in this field.