Abstract
Traditionally, training an end-to-end convolutional neural network (CNN) requires sufficient samples and time cost in dorsal hand vein recognition. In addition, the local features are easy to be lost. Aiming to overcome these shortcomings, a method that fuses features of local binary patterns (LBP) into the ResNet-50 framework using transfer learning is proposed in this paper. Firstly, the texture features encoded by the LBP operator and the pre-processed images are fused. Then, the fused features are input into the ResNet-50 network in a way of transfer learning. Two kinds of vein recognition experiments are carried out to validate the performance of the proposed method, i.e. personal recognition and gender recognition. Dorsal hand vein dataset includes 1928 images collected from left and right hand of 97 volunteers. The experimental results demonstrated that the proposed method achieved superior performance than the classical feature training.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Uhl, A., Busch, C., Marcel, S.: Handbook of Vascular Biometrics. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-27731-4
Kumar, A.: Personal authentication using hand vein triangulation and knuckle shape. IEEE Trans. Image Process. 38(9), 2127–2136 (2009)
Hu, Y.P., Wang, Z.Y.: Hand vein recognition based on the connection lines of reference point and feature point. J. Infrared Phys. Technol. 62(2), 110–114 (2014)
Huang, D., Zhu, X.R.: Dorsal hand vein recognition via hierarchical combination of texture and shape clues. J. Neurocomput. 214, 815 (2016)
Weng, L., Li, X., Wang, W.: Finger vein recognition based on deep convolutional neural networks. In: CISP-BMEI (2020)
Wan, H., Lei, C.: Dorsal hand vein recognition based on convolutional neural networks. In: BIBM (2017)
Al-Johania, N.A., Elrefaei, L.: Dorsal hand vein recognition by convolutional neural networks: feature learning and transfer learning approaches. J. Int. J. Intell. Eng. Syst. 12(3), 171–178 (2019)
Pan, Z., Wang, J.: Hand-dorsa vein recognition based on selective deep convolutional feature. J. IEICE Trans. Inf. Syst. E103D(6), 1423–1426 (2020)
Kuang, H.L., Zhong, Z.H., Liu, X.H.: Palm vein recognition using convolution neural network based on feature fusion with HOG feature. In: ICSGEA (2020)
Wang, Y.D., Huang, S.Y.: Identification of heterogeneous hand vein based on LBP and multi-level structure. Comput. Meas. Control 03, 47 (2017)
Ojala, T.: A comparative study of texture measures with classification based on feature distributions. Pattern Recogn. 29, 51 (1996)
Zhuang, F.Z., Qi, Z.Y.: A comprehensive survey on transfer learning. In: Proceedings of the IEEE (2021)
Liang, H., Fu, W.L.: A survey of recent advances in transfer learning. In: ICCT (2019)
Niu, S.T., Liu, Y.X., Wang, J.: A decade survey of transfer learning (2010–2020). IEEE Trans. Artif. Intell. 1, 151 (2020)
Xu, J.H., Dong, X.Y.: A survey of transfer learning in breast cancer image classification. In: IICSPI (2020)
Ribani, R., Marengoni, M.: A survey of transfer learning for convolutional neural networks. In: SIBGRAPI-T (2019)
Wang, J., Wang, G., Zhou, M.: Bimodal vein data mining via cross-selected-domain knowledge transfer. IEEE Trans. Inf. Forensics Secur. 13, 733 (2017)
Tang, Z.Y., Wang, D., Zhang, Z.Y.: Recurrent neural network training with dark knowledge transfer. In: ICASSP (2016)
Tajbakhsh, N.: Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans. Med. Imag. 35(5), 76 (2016)
Zhou, Z.W.: Fine-tuning convolutional neural networks for biomedical image analysis: actively and incrementally. In: Proceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2017)
Kamble, R.M.: Automated diabetic macular edema (DME) analysis using fine tuning with Inception-Resnet-v2 on OCT images. In: IECBES (2018)
He, K.M., Zhang, X.Y., Ren, S.Q.: Deep residual learning for image recognition. In: CVPR (2016)
Youssef, T.A., Aissam, B., Khalid, D.: Classification of chest pneumonia from x-ray images using new architecture based on ResNet. In: ICECOCS (2020)
Demir, A., Yilmaz, F., Kose, O.: Early detection of skin cancer using deep learning architectures: Resnet-101 and Inception-v3. In: TIPTEKNO (2019)
Singh, A., Goyal, H.: Human identification based on hand dorsal vein pattern using BRISK and SURF algorithm. In: IJEAT (2020)
Xu, J., Yin, J.: Kernel least absolute shrinkage and selection operator regression classifier for pattern classification. Comput. Vis. 7, 55 (2013)
Acknowledgement
This work was supported in part by the National Natural Science Foundation of China under Grant 61471225.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Gu, G. et al. (2021). Dorsal Hand Vein Recognition Based on Transfer Learning with Fusion of LBP Feature. In: Feng, J., Zhang, J., Liu, M., Fang, Y. (eds) Biometric Recognition. CCBR 2021. Lecture Notes in Computer Science(), vol 12878. Springer, Cham. https://doi.org/10.1007/978-3-030-86608-2_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-86608-2_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86607-5
Online ISBN: 978-3-030-86608-2
eBook Packages: Computer ScienceComputer Science (R0)