Abstract
This paper proposes a computationally efficient palm and wrist vein biometric system through finely tuning computer-vision algorithms. In particular, a comprehensive analysis of the scale-invariant feature transform (SIFT) and speeded-up robust features (SURF) keypoint descriptors was conducted along with a novel idea of a score-based fusion of directional image derivatives to achieve outstanding recognition results. The work demonstrates that appropriate vein image processing, keypoint extraction, optimal matching metrics, and combination of classification scores from a group of directional gradients lead to robust and stable vein recognition. It was shown through experimental analysis that the developed biometric system outperforms all state-of-the-art results other than deep learning methods on the two public hand vein databases (VERA and PUT). Moreover, an absolute 100% recognition for the PUT palm dataset was achieved without using deep learning. The proposed method is more suitable for embedded implementation compared to deep learning algorithms, with only a slight penalty in performance compared to deep learning architectures.
Similar content being viewed by others
References
Ahmed MA, El-Horbaty E-SM, Salem A-BM (2015) Intelligent techniques for matching palm vein images. Egyptian Computer Science Journal 39:1–14
Ananthi G, Sekar JR, Arivazhagan S (2021) Human palm vein authentication using curvelet multiresolution features and score level fusion. Vis Comput:1–14
Arakala A, Hao H, Davis S, Horadam K (2015) The palm vein graph - feature extraction and matching. In: International Conference on Information Systems Security and Privacy. SCITEPRESS - Science and and Technology Publications, pp 56–64
Babalola FO, Bitirim Y, Toygar Ö (2021) Palm vein recognition through fusion of texture-based and CNN-based methods. SIViP 15:459–466
Bay H, Tuytelaars T, Van Gool L (2006) SURF: Speeded Up Robust Features. In: SURF: speeded up robust features. Springer, Berlin, Heidelberg, pp 404–417
Bouzida N, Bendada AH, Maldague XP (2010) Near-infrared image formation and processing for the extraction of hand veins. J Mod Opt 57:1731–1737. https://doi.org/10.1080/09500341003725763
Bradski G, Kaehler A, Cambridge B·, et al (2008) Learning OpenCV. O’Reilly Media Inc.
Chen Y-Y, Hsia C-H, Chen P-H (2021) Contactless multispectral palm-vein recognition with lightweight convolutional neural network. IEEE Access 9:149796–149806
Cho S, Oh BS, Kim D, Toh KA (2021) Palm-vein verification using images from the visible Spectrum. IEEE Access
Coetzee L, Botha EC (1993) Fingerprint recognition in low quality images. Pattern Recogn 26:1441–1460. https://doi.org/10.1016/0031-3203(93)90151-L
Das A, Pal U, Ballester MAF, Blumenstein M (2014) A new wrist vein biometric system. In: 2014 IEEE symposium on computational intelligence in biometrics and identity management (CIBIM). IEEE, pp 68–75
Du G, Su F, Cai A (2009) Face recognition using SURF features. In: Ding M, Bhanu B, Wahl FM, Roberts J (eds) SPIE 7496, MIPPR 2009: pattern recognition and computer vision, 749628. International Society for Optics and Photonics, pp 749628–749634
Hartung D, Olsen MA, Xu H, Busch C (2011) Spectral minutiae for vein pattern recognition. In: 2011 international joint conference on biometrics (IJCB). IEEE, pp 1–7
Jain A, Lin H, Bolle R (1997) On-line fingerprint verification. IEEE Trans Pattern Anal Mach Intell 19:302–314. https://doi.org/10.1109/34.587996
Jain AK, Bolle R, Pankanti S (2006) Biometrics : personal identification in networked society. Springer Science & Business Media
Jhong S-Y, Tseng P-Y, Siriphockpirom N, Hsia C-H, Huang M-S, Hua K-L, Chen Y-Y (2020) An automated biometric identification system using CNN-based palm vein recognition. In: 2020 international conference on advanced robotics and intelligent systems (ARIS). IEEE, pp 1–6
Kabaciński R, Kowalski M (2011) Vein pattern database and benchmark results. Electron Lett 47:1127–1128. https://doi.org/10.1049/el.2011.1441
Kang W, Wu Q (2014) Contactless palm vein recognition using a mutual foreground-based local binary pattern. IEEE Transactions on Information Forensics and Security 9:1974–1985. https://doi.org/10.1109/TIFS.2014.2361020
Kong WK, Zhang D, Li W (2003) Palmprint feature extraction using 2-D Gabor filters. Pattern Recogn 36:2339–2347. https://doi.org/10.1016/S0031-3203(03)00121-3
Kumar R, Singh RC, Kant S (2021) Dorsal hand vein-biometric recognition using convolution neural network. In: International Conference on Innovative Computing and Communications. Springer, pp 1087–1107
Li W, Zhang D, Xu Z (2002) Palmprint identification by fourier transform. Int J Pattern Recognit Artif Intell 16:417–432. https://doi.org/10.1142/S0218001402001757
Lindeberg T (1994) Scale-space theory: a basic tool for analyzing structures at different scales. J Appl Stat 21:225–270. https://doi.org/10.1080/757582976
Lowe DG (2004) Distinctive image features from scale-invariant Keypoints. Int J Comput Vis 60:91–110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
Ma X, Jing X, Huang H, Cui Y, Mu J (2017) Palm vein recognition scheme based on an adaptive Gabor filter. IET Biometrics 6:325–333
Mirmohamadsadeghi L, Drygajlo A (2014) Palm vein recognition with local texture patterns. IET Biometrics 3:198–206. https://doi.org/10.1049/iet-bmt.2013.0041
Nivas S, Prakash P (2014) Real-time finger-vein recognition system. International Journal of Engineering Research and General Science 2:580–591
Olsen MA, Hartung D, Busch C, Larsen R (2010) Contrast enhancement and metrics for biometric vein pattern recognition. In: International conference on intelligent computing. Springer, Berlin, Heidelberg, pp 425–434
Pan M, Kang W (2011) Palm vein recognition based on three local invariant feature extraction algorithms. In: Chinese conference on biometric recognition. Springer, Berlin, Heidelberg, pp 116–124
Pedersen JT (2011) Study group SURF: feature detection and description. Department of Computer Science, Aarhus University
Raghavendra R, Surbiryala J, Busch C (2015) Hand dorsal vein recognition: sensor, algorithms and evaluation. In: 2015 IEEE international conference on imaging systems and techniques (IST). IEEE, pp 1–6
Sangeetha NM, Kumar TA, Natarajan DM (2014) Feature level fusion of WLBP and HOG for hand dorsal vein recognition. International Journal of Emerging Technology and Advanced Engineering 4:9–17
Shark L-K, Zhang K, Wang Y (2014) Personal identification based on multiple keypoint sets of dorsal hand vein images. IET Biometrics 3:234–245. https://doi.org/10.1049/iet-bmt.2013.0042
Tome P, Marcel S (2015) Palm vein database and experimental framework for reproducible research. In: 2015 international conference of the biometrics special interest group (BIOSIG). IEEE, pp 1–7
Wang G, Wang J (2017) SIFT based vein recognition models: analysis and improvement. Computational and Mathematical Methods in Medicine 2017:1–14. https://doi.org/10.1155/2017/2373818
Wang K, Zhang Y, Yuan Z, Zhuang D (2006) Hand vein recognition based on multi supplemental features of multi-classifier fusion decision. In: 2006 international conference on mechatronics and automation. IEEE, pp 1790–1795
Wang Y, Li K, Shark L, Varley MR (2011) Hand-Dorsa Vein Recognition Based on Coded and Weighted Partition Local Binary Patterns. In: 2011 International Conference on Hand-Based Biometrics. IEEE, pp 1–5
Wu W, Elliott SJ, Lin S, Sun S, Tang Y (2019) Review of palm vein recognition. IET Biometrics 9:1–10
Xueyan L, Shuxu G (2008) The fourth biometric - vein recognition. In: Pattern recognition techniques, technology and applications. InTech, pp 537–546
Zhou Y, Kumar A (2011) Human identification using palm-vein images. IEEE Transactions on Information Forensics and Security 6:1259–1274. https://doi.org/10.1109/TIFS.2011.2158423
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Alshayeji, M.H., Al-Roomi, S.A. & Abed, S. Efficient hand vein recognition using local keypoint descriptors and directional gradients. Multimed Tools Appl 81, 15687–15705 (2022). https://doi.org/10.1007/s11042-022-12608-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12608-6