Deep Learning Techniques for Hand Vein Biometrics: A Comprehensive Review

TL;DR

The paper surveys deep learning approaches for hand vein biometrics across finger vein, palm vein, dorsal hand vein, and multimodal vein systems, with emphasis on DL-based preprocessing, feature extraction, matching, and security components such as PAD and template protection. It highlights dataset limitations, data augmentation and transfer learning as key enablers for small-scale vein datasets, and provides a taxonomy of FV, PV, and DHV DL methods along with multimodal fusion strategies. The review catalogs publicly available datasets and evaluation metrics, and discusses practical considerations including data quality, acquisition modes, and cross-device generalization. It also outlines significant challenges—data scarcity, variability, and security concerns—and offers future directions such as synthetic data generation, 3D vein recognition, FL, DRL/GNN, integrity assurance, IoT applications, and Transformer/LLM-driven approaches to advance the field. Overall, the work positions hand vein biometrics as a secure, contactless modality with strong potential for robust DL-based authentication, while calling for broader datasets, standardized benchmarks, and innovative architectures to realize real-world deployment.

Abstract

Biometric authentication has garnered significant attention as a secure and efficient method of identity verification. Among the various modalities, hand vein biometrics, including finger vein, palm vein, and dorsal hand vein recognition, offer unique advantages due to their high accuracy, low susceptibility to forgery, and non-intrusiveness. The vein patterns within the hand are highly complex and distinct for each individual, making them an ideal biometric identifier. Additionally, hand vein recognition is contactless, enhancing user convenience and hygiene compared to other modalities such as fingerprint or iris recognition. Furthermore, the veins are internally located, rendering them less susceptible to damage or alteration, thus enhancing the security and reliability of the biometric system. The combination of these factors makes hand vein biometrics a highly effective and secure method for identity verification. This review paper delves into the latest advancements in deep learning techniques applied to finger vein, palm vein, and dorsal hand vein recognition. It encompasses all essential fundamentals of hand vein biometrics, summarizes publicly available datasets, and discusses state-of-the-art metrics used for evaluating the three modes. Moreover, it provides a comprehensive overview of suggested approaches for finger, palm, dorsal, and multimodal vein techniques, offering insights into the best performance achieved, data augmentation techniques, and effective transfer learning methods, along with associated pretrained deep learning models. Additionally, the review addresses research challenges faced and outlines future directions and perspectives, encouraging researchers to enhance existing methods and propose innovative techniques.

Figures (11)

• Figure 1: Biometrics of hands jaswal2016knuckle. (a) Palm hand features. (b) Dorsal hand features. These characteristics serve as unique biometric identifiers for accurate and reliable personal identification and authentication.
• Figure 2: Roadmap of the review, showing main sections of the manuscript.
• Figure 3: Word cloud of the most essential terms in the field of hand vein biometrics.
• Figure 4: Improved caption: Bibliography Statistics: (a) Annual publications on DL-based hand vein research; (b) Percentage distribution of publications across different domains: FV, PV, DHV, and multi-modal. The data clearly indicates a predominant research focus on DL-based FV.
• Figure 5: DTL principles. (a) Full fine-tuning; (b) Partial fine-tuning; (c) DA.