Abstract
Finger is a very competent biometric carrier, which contains many valuable biometric features (fingerprint, finger-vein and finger-knuckle-print). Exploring multi-modal biometric fusion recognition of fingers is very meaningful for improving the security and stability of finger feature expression. Due to the differences in the expression of different modal features, the interaction mode and fusion strategy between different modalities are the key to finger multi-modal biometrics. Recently, we note that Transformer exhibits strong performance in natural language processing and computer vision. In this paper, a Transformer based finger tri-modal fusion and recognition framework, termed TransFinger, is proposed, where Transformer attention is employed to calculate the interaction response among the three modalities of the finger, and from this, the channel and spatial attentions of different modalities are generated. To the best of our knowledge, it is the first to apply Transformer attention to implement the fusion and recognition of finger biometrics. At the same time, with only minor changes, the TransFinger framework has good generalization for the number of fused modalities. Simulation results have demonstrated the effectiveness of the proposed finger tri-modal fusion and recognition framework.
This work was supported by the Shenzhen Science and Technology Program (No. RCBS20200714114940262), National Natural Science Foundation of China (No. 61806208 and 62076166).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhao, Q., Zhang, L., Zhang, D., et al.: Adaptive pore model for fingerprint pore extraction. In: 2008 19th International Conference on Pattern Recognition, pp. 1–4. IEEE (2008)
Wang, L., Zhang, H., Yang, J.: Finger multimodal features fusion and recognition based on CNN. In: 2019 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 3183–3188. IEEE (2019)
Yang, J., Zhong, Z., Jia, G., et al.: Spatial circular granulation method based on multimodal finger feature. J. Electr. Comput. Eng. 2016, 1–7 (2016)
Yang, J., Zhang, X.: Feature-level fusion of fingerprint and finger-vein for personal identification. Pattern Recogn. Lett. 33(5), 623–628 (2012)
Li, S., Zhang, H., Shi, Y., et al.: Novel local coding algorithm for finger multimodal feature description and recognition. Sensors 19(9), 2213 (2019)
Gu, J., Wang, Z., Kuen, J., et al.: Recent advances in convolutional neural networks. Pattern Recogn. 77, 354–377 (2018)
Wen, M., Zhang, H., Yang, J.: End-to-end finger trimodal features fusion and recognition model based on CNN. In: Feng, J., Zhang, J., Liu, M., Fang, Y. (eds.) CCBR 2021. LNCS, vol. 12878, pp. 39–48. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86608-2_5
Zhang, S., Tong, H., Xu, J., et al.: Graph convolutional networks: a comprehensive review. Comput. Soc. Netw. 6(1), 1–23 (2019)
Qu, H., Zhang, H., Yang, J., Wu, Z., He, L.: A generalized graph features fusion framework for finger biometric recognition. In: Feng, J., Zhang, J., Liu, M., Fang, Y. (eds.) CCBR 2021. LNCS, vol. 12878, pp. 267–276. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86608-2_30
Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16 \(\times \) 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Kaur, M., Singh, M., Girdhar, A., et al.: Fingerprint verification system using minutiae extraction technique. World Acad. Sci. Eng. Technol. 46, 497–502 (2008)
Masmoudi, A.D., Masmoudi, D.S.: Implementation of a fingerprint recognition system using LBP descriptor. J. Test. Eval. 38(3), 369–382 (2010)
Zeng, F., Hu, S., Xiao, K.: Research on partial fingerprint recognition algorithm based on deep learning. Neural Comput. Applicat. 31(9), 4789–4798 (2019)
Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971–987 (2002)
Liu, F., Yang, G., Yin, Y., et al.: Singular value decomposition based minutiae matching method for finger vein recognition. Neurocomputing 145, 75–89 (2014)
Liu, W., Li, W., Sun, L., et al.: Finger vein recognition based on deep learning. In: 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA), pp. 205–210. IEEE (2017)
Woodard, D.L., Flynn, P.J.: Finger surface as a biometric identifier. Comput. Vis. Image Understand. 100(3), 357–384 (2005)
Zhao, Z., Ye, Z., Yang, J., Zhang, H.: Finger crystal feature recognition based on graph convolutional network. In: Feng, J., Zhang, J., Liu, M., Fang, Y. (eds.) CCBR 2021. LNCS, vol. 12878, pp. 203–212. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86608-2_23
Patil, V.H., Dhole, M.R.S.S.A.: An efficient secure multimodal biometric fusion using palm print and face image. Int. J. Appl. Eng. Res. 11(10), 7147–7150 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, Z., Zhang, H., Chen, Z., Yang, J. (2022). TransFinger: Transformer Based Finger Tri-modal Biometrics. In: Deng, W., et al. Biometric Recognition. CCBR 2022. Lecture Notes in Computer Science, vol 13628. Springer, Cham. https://doi.org/10.1007/978-3-031-20233-9_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-20233-9_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20232-2
Online ISBN: 978-3-031-20233-9
eBook Packages: Computer ScienceComputer Science (R0)