A Deep Biometric Hash Learning Framework for Three Advanced Hand-based Biometrics

Hand-based biometrics have undergone extensive research in recent decades. Besides fingerprint, which is commonly used in personal authentication, there are other three advanced hand-based biometrics being further researched worldwide, palmprint, palm vein, and dorsal hand vein. However, academics mainly focus on their unimodal or multimodal recognitions, and few researchers conduct comprehensive comparisons for them to guide practical applications, i.e. which one is the suitable biometric modality. Inspired by Deep Hashing Network (DHN) and transfer learning, we propose a Deep Biometric Hash Learning (DBHL) framework to uniformly analyze and deal with these three biometrics. An end-to-end network is involved to convert images into binary codes. Pre-trained network is employed for fine-tuning, and Hamming distance is adopted to measure the similarity between the codes of query and registration images. Through experiments on benchmarks, Equal Error Rate (EER) and the maximum or minimum distance of genuines or imposters are obtained as performance metrics. In experiments, EERs of palmprint and palm vein recognitions reach 0%, and EER of dorsal hand vein recognition is as low as 0.196%. It shows DBHL framework is effective to construct hand-based biometrics systems. Furthermore, a plain comparison among them shows that palmprint is more suitable in practical applications.