Part of the book series:Lecture Notes in Computer Science ((LNIP,volume 12878))
Included in the following conference series:
1680Accesses
Abstract
Finger which contains abundant biometric information, has played an important role in the field of identification recognition. Due to the complexity of fingerprint (FP), finger-vein (FV) and finger-knuckle (FKP), traditional feature-level fusion methods perform poorly. This paper proposed an end-to-end finger trimodal features fusion and recognition model based on CNN. For the purpose of constructing an end-to-end model, finger three-modal features extraction module and finger trimodal features fusion module are embedded in CNN. The finger three-modal features extraction module is composed of three parallel and independent CNNs, which are used to extract features from finger trimodal images separately. The finger trimodal features fusion module contains two convolution layers, through which fusion feature can be obtained. The experimental results show that the model proposed in this paper can get high recognition accuracy 99.83%. It shows that the fusion feature obtained by the proposed model possessing good individual characterization ability can effectively improve recognition accuracy.
This is a preview of subscription content,log in via an institution to check access.
Access this chapter
Subscribe and save
- Get 10 units per month
- Download Article/Chapter or eBook
- 1 Unit = 1 Article or 1 Chapter
- Cancel anytime
Buy Now
- Chapter
- JPY 3498
- Price includes VAT (Japan)
- eBook
- JPY 9151
- Price includes VAT (Japan)
- Softcover Book
- JPY 11439
- Price includes VAT (Japan)
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kien, N., Clinton, F., Sridha, S., et al.: Super-Resolution for biometrics: a comprehensive survey. Pattern Recogn. J. Pattern Recogn. Soc.78, 23–42 (2018)
Shaikh, J., Uttam, D.: Review of hand feature of unimodal and multimodal biometric system. Int. J. Comput. Appl.133(5), 19–24 (2016)
Asaari, M.S.M., Suandi, S.A., Rosdi, B.A.: Fusion of band limited phase only correlation and width centroid contour distance for finger based biometrics. Expert Syst. Appl.41(7), 3367–3382 (2014)
Loffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprintarXiv:150203167 (2015)
Fang Yuxun, W., Qiuxia, K.W.: A novel finger vein verification system based on two-stream convolutional network learning. Neurocomputing290, 100–107 (2018)
Qin, H.F., El-Yacoubi, M.A.: Deep representation-based feature extraction and recovering for finger-vein verification. IEEE Trans. Inf. Forensics Secur.12(8), 1816–1829 (2017)
Tang, S., Zhou, S., Kang, W.X., et al.: Finger vein verification using a Siamese CNN. IET Biom.8(5), 306–315 (2019)
Hou, B.R., Yan, R.Q.: Convolutional auto-encoder model for finger-vein verification. IEEE Trans. Instrum. Meas.64(5), 2067–2074 (2020)
Wang, A.R., Cai, J.F., Ji, W.L., et al.: MMSS: Multi-modal sharable and specific feature learning for RGB-D object recognition. In: Proceedings of the IEEE International Conference on Computer Vision, Santiago, pp. 125–1133 (2015)
Wang, A.R., Lu, J.W., Cai, J.F., et al.: Large-margin multimodal deep learning for RGB-D object recognition. IEEE Trans. Multimedia17(11), 1887–1898 (2015)
Zhang, H., Han, H., Cui, J.Y., et al.: RGB-D face recognition via deep complementary and common feature learning. In: IEEE International Conference on Automatic Face & Gesture Recognition, pp. 8–15. IEEE Computer Society (2018)
Sobhan, S., Ali, D., Hadi, K., et al.: Multi-level feature abstraction from convolutional neural networks for multimodal biometric identification. In: 24th International Conference on Pattern Recognition (2018)
Zhang, H.G., Li, S.Y., Shi, Y.H.: Graph fusion for finger multimodal biometrics. IEEE Access, 28607–28615 (2019)
Bai, G.Y., Yang, J.F.: A new pixel-based granular fusion method for finger recognition. In: Eighth International Conference on Digital Image Processing. International Society for Optics and Photonics (2016)
Li, S.Y., Zhang, H.G., Yang, J.F.: Novel local coding algorithm for finger multimodal feature description and recognition. Sensors19, 2213 (2019)
Acknowledgments
This work was supported in part by the National Natural Science Foundation of China under Grant 62076166 and 61806208, in part by the Rural Science and Technology Commissioner Project of Guangdong Provincial Science and Technology Department under Grant KPT20200220.
Author information
Authors and Affiliations
Institute of Applied Artificial Intelligence of the Guangdong-HongKong-Macao Greater Bay Area, Shenzhen Polytechnic, Shenzhen, 518000, Guangdong, China
Mengna Wen, Haigang Zhang & Jinfeng Yang
- Mengna Wen
You can also search for this author inPubMed Google Scholar
- Haigang Zhang
You can also search for this author inPubMed Google Scholar
- Jinfeng Yang
You can also search for this author inPubMed Google Scholar
Corresponding author
Correspondence toHaigang Zhang.
Editor information
Editors and Affiliations
Tsinghua University, Beijing, China
Jianjiang Feng
Fudan University, Shanghai, China
Junping Zhang
Shanghai Jiao Tong University, Shanghai, China
Manhua Liu
Shanghai University, Shanghai, China
Yuchun Fang
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wen, M., Zhang, H., Yang, J. (2021). End-To-End Finger Trimodal Features Fusion and Recognition Model Based on CNN. 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_5
Download citation
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)
Share this paper
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative