Using a Lightweight Convolutional Neural Network for Contactless Multispectral Palm-Vein Recognition

  • Komal Teotia
  • Dr. Manav Bansal
Keywords: Biometric, palm-vein identification, convolution neural networks, triplicate loss function, handcrafted character


Biometric recognition technology has advanced to the point of replacing traditional codes and credentials. One such technique gaining popularity is contactless palm vein verification, which is safe and sanitary. However, there are important issues to consider regarding system safety and scalability in deep learning (DL). Convolutional neural networks (CNNs) are among the most extensively studied deep learning algorithms, known for their ability to extract features. Nonetheless, training CNNs requires a significant intellectual effort and large sample sizes, resulting in higher hardware and software costs.To address the need for a substantial amount of palm-vein data, this research proposes to use a versatile Gabor filter with improved photographic characteristics and a triplet loss function. 

This study used a multidimensional palm database from the CASIA accessible database to evaluate the suggested system. According to the study findings, the suggested approach only requires a small number of network configurations in a multispectral environment and has an average identification error rate of 0.0456%.

Author Biographies

Komal Teotia

Scholar M.Tech CSE, SCRIET, Chaudhary Charan Singh University, Meerut, India

Dr. Manav Bansal

Assistant Professor, SCRIET, Chaudhary Charan Singh University, Meerut, India


1. W. Kang and Q. Wu, ``Contactless palm vein recognition using a mutual foreground-based local binary pattern,'' IEEE Trans. Inf. Forensics Security, vol. 9, no. 11, pp. 1974_1985, Nov. 2014.
2. C.-H. Hsia, J.-S. Chiang, and C.-Y. Lin, ``A face detection method for illumination variant condition,'' Scientia Iranica, vol. 22, no. 6,pp. 2081_2091, 2015.
3. D. Menotti, G. Chiachia, A. Pinto, W. R. Schwartz, H. Pedrini, A. X. Falcao, and A. Rocha, ``Deep representations for iris, face, an fingerprint spoofing detection,'' IEEE Trans. Inf. Forensics Security,vol. 10, no. 4, pp. 864_879, Apr. 2015.
4. S. Cho, B.-S. Oh, K.-A. Toh, and Z. Lin, ``Extraction and cross-matching of palm-vein and palm print from the RGB and the NIR spectrums for identity verification,'' IEEE Access, vol. 8, pp. 4005_4021, 2020.
5. C.-H. Hsia, ``New verification strategy for finger-vein recognition system,'' IEEE Sensors J., vol. 18, no. 2, pp. 790_797, Jan. 2018.
6. C.-H. Hsia, ``Improved finger-vein pattern method using wavelet-based for real-time personal identification system,'' J. Imag. Sci. Technol., vol. 26, no. 3, p. 30402, 2018.
7. Y. Zhou and A. Kumar, ``Human identification using palm-vein images,''IEEE Trans. Inf. Forensics Security, vol. 6, no. 4, pp. 1259_1274,Dec. 2011.
8. F. Liu, S. Jiang, B. Kang, and T. Hou, ``A recognition system for partiallyoccluded dorsal hand vein using improved biometric graph matching,''IEEE Access, vol. 8, pp. 74525_74534, 2020.
9. O. Toygar, F. O. Babalola, and Y. Bitirim, ``FYO: A novel multimodal veindatabase with palmar, dorsal and wrist biometrics,'' IEEE Access, vol. 8,pp. 82461_82470, 2020.
10. M. Zhou, L. Lin, M. Wang, X. Li, and G. Li, ``Infiuence of water on noninvasive hemoglobin measurement by dynamic spectrum,'' Anal. Methods, vol. 5, no. 18, pp. 4660_4665, 2013.
11. J.-D. Wu and S.-H. Ye, ``Driver identification using finger-vein patterns with Radon transform and neural network,'' Expert Syst. Appl., vol. 36,no. 3, pp. 5793_5799, Apr. 2009.
12. W.Wu, S. J. Elliott, S. Lin, andW. Yuan, ``Low-cost biometric recognition system based on NIR palm vein image,'' IET Biometrics, vol. 8, no. 3,pp. 206_214, May 2019.
13. F. O. Babalola, Y. Bitirim, and Ö. Toygar, ``Palm vein recognition throughfusion of texture-based and CNN-based methods,'' Signal, Image Video Process., vol. 15, pp. 1_8, Apr. 2020.
14. H. Zhang, C. Tang, A.W.-K. Kong, and N. Craft, ``Matching vein patterns from color images for forensic investigation,'' in Proc. IEEE 5th Int. Conf.Biometrics, Theory, Appl. Syst. (BTAS), Sep. 2012, pp. 77_84.
15. N. Miura, A. Nagasaka, and T. Miyatake, ``Extraction of finger-vein patterns using maximum curvature points in image profiles,'' IEICE Trans.Inf. Syst., vol. 90, no. 8, pp. 1185_1194, Aug. 2007.
16. L. Mirmohamadsadeghi and A. Drygajlo, ``Palm vein recognition with local binary patterns and local derivative patterns,'' in Proc. Int. Joint Conf.
17. Biometrics (IJCB), Washington, DC, USA, Oct. 2011, pp. 1_6.
18. E. C. Lee, H. C. Lee, and K. R. Park, ``Finger vein recognition using minutiabased alignment and local binary pattern-based feature extraction,'' Int. J. Imag. Syst. Technol., vol. 19, no. 3, pp. 179_186, 2009.
19. X. Li, S. Guo, F. Gao, and Y. Li, ``Vein pattern recognitions by moment invariants,'' in Proc. 1st Int. Conf. Bioinf. Biomed. Eng., Wuhan, China, Jul. 2007, pp. 612_615.
20. W. Kang, Y. Liu, Q.Wu, and X. Yue, ``Contact-free palm-vein recognition based on local invariant features,'' PLoS ONE, vol. 9, no. 5, pp. 1_12, 2014.
21. D. Thapar, G. Jaswal, A. Nigam, and V. Kanhangad, ``PVSNet: Palm vein authentication Siamese network trained using triplet loss and adaptive hard mining by learning enforced domain specific features,'' in Proc. IEEE 5th Int.
22. Conf. Identity, Secur., Behav. Anal. (ISBA), Hyderabad, India, Jan. 2019, pp. 1_8. [21] R. Das, E. Piciucco, E. Maiorana, and P. Campisi, ``Convolutional neural network for finger-vein-based biometric identification,'' IEEE Trans. Inf. Forensics Security, vol. 14, no. 2, pp. 360_373, 2019.
23. Y. Fang, Q. Wu, and W. Kang, ``A novel finger vein verification system based on two-stream convolutional network learning,'' Neurocomputing, vol. 290, pp. 100_107, May 2018.
24. C.-H. Hsia and C.-F. Lai, ``Embedded vein recognition system with wavelet domain,'' Sensors Mater., vol. 32, no. 10, pp. 3221_3234, 2020.
25. R. Mehrotra, K. R. Namuduri, and N. Ranganathan, ``Gabor filterbased edge detection,'' Pattern Recognit., vol. 25, no. 12, pp. 1479_1494,Dec. 1992. [25] J.-C. Lee, C.-H. Lee, C.-B. Hsu, P.-Y.Kuei, and K.-C. Chang, ``Dorsal hand vein recognition based on 2D Gabor filters,'' Imag. Sci. J., vol. 62, no. 3,pp. 127_138, 2014.
26. [26] W.-Y. Han and J.-C. Lee, ``Palm vein recognition using adaptive Gabor filter,'' Expert Syst. Appl., vol. 39, no. 18, pp. 13225_13234, Dec. 2012. [27] X. Ma, X. Jing, H. Huang, Y. Cui, and J. Mu, ``Palm vein recognition scheme based on an adaptive Gabor filter,'' IET Biometrics, vol. 6, no. 5, pp. 325_333, 2017.
27. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei, ``ImageNet large scale visual recognition challenge,'' 2014, arXiv:1409.0575.
28. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, ``MobileNetV2: Inverted residuals and linear bottlenecks,'' in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., Jun. 2018, pp. 4510_4520.
29. K. Simonyan and A. Zisserman, ``Very deep convolutional networks for large-scale image recognition,'' 2014, arXiv:1409.1556.
30. S. Tang, S. Zhou,W. Kang, Q. Wu, and F. Deng, ``Finger vein verification using a Siamese CNN,'' IET Biometrics, vol. 8, no. 5, pp. 306_315, Sep. 2019. [32] CASIA Palm Image Database. Accessed: Jul. 15, 2018. [Online]. Available:
31. X. Yan, W. Kang, F. Deng, and Q. Wu, ``Palm vein recognition based on multi-sampling and feature-level fusion,'' Neurocomputing, vol. 151, pp. 798_807, Mar. 2015.
32. S. Bhilare, G. Jaswal, V. Kanhangad, and A. Nigam, ``Single-sensor handvein multimodal biometric recognition using multiscale deep pyramidal approach,'' Mach. Vis. Appl., vol. 29, no. 8, pp. 1269_1286, Nov. 2018.
33. K. J. Noh, J. Choi, J. S. Hong, and K. R. Park, ``Finger-vein recognition based on densely connected convolutional network using score-level fusion with shape and texture images,'' IEEE Access, vol. 8, pp. 96748_96766,2020.
34. W. Kim, J. M. Song, and K. R. Park, ``Multimodal biometric recognition based on convolutional neural network by the fusion of finger-vein and finger shape using near-infrared (NIR) camera sensor,'' Sensors, vol. 18, no. 7, p. 2296, 2018.
35. E. Jalilian and A. Uhl, ``Finger-vein recognition using deep fully convolutional neural semantic segmentation networks: The impact of training data,'' in Proc. IEEE Int. Workshop Inf. Forensics Secur., Dec. 2018, pp. 1_8. [38] R. Kabacinski and K. Kowalski, ``Vein pattern database and benchmark results,'' Electron. Lett., vol. 47, no. 20, pp. 1127_1128, 2011.
36. [39] G. Wang and J. Wang, ``SIFT based vein recognition models: Analysis and improvement,'' Comput. Math. Methods Med., vol. 2017, pp. 1_14, Jun. 2017. [40] S. Bharathi and R. Sudhakar, ``Biometric recognition using finger and palm vein images,'' Soft Comput., vol. 23, no. 6, pp. 1843_1855, Mar. 2019.
37. F. Ahmad, L.-M. Cheng, and A. Khan, ``Lightweight and privacypreserving template generation for palm-vein-based human recognition,'' IEEE Trans. Inf. Forensics Security, vol. 15, pp. 184_194, 2020.
38. G. Wang, C. Sun, and A. Sowmya, ``Multi-weighted co-occurrence descriptor encoding for vein recognition,'' IEEE Trans. Inf. Forensics Security, vol. 15, pp. 375_390, 2020.
39. Z. Pan, J. Wang, G. Wang, and J. Zhu, ``Multi-scale deep representation aggregation for vein recognition,'' IEEE Trans. Inf. Forensics Security, vol. 16, pp. 1_15, 2021.
40. H. Wan, L. Chen, H. Song, and J. Yang, ``Dorsal hand vein recognition based on convolutional neural networks,'' in Proc. IEEE Int. Conf. Bioinf. Biomed. (BIBM), Nov. 2017, pp. 1215_1221.
41. C.-H. Hsia, J.-M. Guo, and C.-S. Wu, ``Finger-vein recognition based on parametric-oriented corrections,'' Multimedia Tools Appl., vol. 76, no. 23, pp. 25179_25196, Dec. 2017.
42. T. E. Boult, ``PICO: Privacy through invertible cryptographic obscuration,'' in Proc. Comput. Vis. Interact. Intell. Environ. (CVIIE), Nov. 2005, pp. 27_38.
43. V. G. Moshnyaga, J. Shioyama, and K. Hashimoto, ``A camera-based approach to prevent fingerprint hacking,'' in Proc. IEEE Int. Workshop Signal Process. Syst., Oct. 2018, pp. 235_240.
44. K. Shaheed, H. Liu, G. Yang, I. Qureshi, J. Gou, and Y. Yin, ``A systematic review of finger vein recognition techniques,'' Information, vol. 9, no. 9,p. 213, Aug. 2018.
45. L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, ``Encoderdecoder with atrous separable convolution for semantic image segmentation,'' in Proc. Eur. Conf. Comput. Vis., Munich, Germany, 2018, pp. 833_851.
46. P. Wang and H. Qin, ``Palm-vein verification based on U-Net,'' IOP Conf. Mater. Sci. Eng., vol. 806, Apr. 2020, Art. no. 012043.
47. M. I. Obayya, M. El-Ghandour, and F. Alrowais, ``Contactless palm vein authentication using deep learning with Bayesian optimization,'' IEEE Access, vol. 9, pp. 1940_1957, 2021.
48. M. El-Ghandour, M. I. Obayya, B. Yousef, and N. F. Areed, ``Palmvein recognition using block-based WLD histogram of Gabor feature maps and deep neural network with Bayesian optimization,'' IEEE Access, vol. 9, pp. 97337_97353, 2021.
How to Cite
Komal Teotia, & Dr. Manav Bansal. (2024). Using a Lightweight Convolutional Neural Network for Contactless Multispectral Palm-Vein Recognition. Revista Electronica De Veterinaria, 25(1S), 60-75. Retrieved from