Abstract
Compared with single-mode biometric recognition, multimodal biometric recognition has been widely used because of its high security and high accuracy. Among them, finger based multimodal biometric recognition is the most common and efficient way. However, biometric recognition has lots of problems such as too high feature dimensions, high computational complexity and insufficient correlation between modal classes. This paper propose an improved DenseNet network, which uses dual channel input and feature layer fusion to obtain richer features. Then, in order to make the network learn the multimodal representation adaptively, we introduce the attention mechanism and optimize the loss function. The network solves the problem of performance degradation caused by insufficient correlation between different modes in the fusion process, and it can effectively improve the recognition accuracy. Finally, we verify it on two public multimodal datasets and achieve good results.
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
References
Yin, X., Zhu, Y., Hu, J.: Contactless fingerprint recognition based on global minutia topology and loose genetic algorithm. IEEE Trans. Inf. Foren. Secur. 15, 28–41 (2019)
Al-Waisy, A.S., Qahwaji, R., Ipson, S., Al-Fahdawi, S., Nagem, T.A.M.: A multi-biometric iris recognition system based on a deep learning approach. Pattern Anal. Appl. 21(3), 783–802 (2017). https://doi.org/10.1007/s10044-017-0656-1
Chandrakala, M., Durga Devi, P.: Two-stage classifier for face recognition using HOG features. Materials Today: Proceedings (2021)
Banerjee, A., Basu, S., Basu, S., Nasipuri, M.: ARTeM: a new system for human authentication using finger vein images. Multimedia Tools Appl. 77(5), 5857–5884 (2018)
Lu, Y., Yoon, S., Wu, S., Park, D.S.: Pyramid histogram of double competitive pattern for finger vein recognition. IEEE Access 6, 56445–56456 (2018)
Prommegger, B., Wimmer, G., Uhl, A.: Rotation tolerant finger vein recognition using CNNs. In: 2021 International Conference of the Biometrics Special Interest Group (BIOSIG), pp. 1–5. IEEE (2021)
Kuzu, R. S., Maiorana, E., Campisi, P.: Loss functions for CNN-based biometric vein recognition. In: 2020 28th European Signal Processing Conference (EUSIPCO), pp. 750–754. IEEE (2021)
Song, J.M., Kim, W., Park, K.R.: Finger-vein recognition based on deep DenseNet using composite image. IEEE Access 7, 66845–66863 (2019)
Leng, L., Li, M., Kim, C., Bi, X.: Dual-source discrimination power analysis for multi-instance contactless palmprint recognition. Multimedia Tools Appl. 76(1), 333–354 (2015). https://doi.org/10.1007/s11042-015-3058-7
Leng, L., Zhang, J.: Palmhash code vs. palmphasor code. Neurocomputing 108, 1–12 (2013)
Talo, M.: Automated classification of histopathology images using transfer learning. Artif. Intell. Med. 101, 101743 (2019)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Sun, Y., et al.: Circle loss: a unified perspective of pair similarity optimization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6398–6407 (2020)
Yin, Y., Liu, L., Sun, X.: SDUMLA-HMT: a multimodal biometric database. In: Sun, Z., Lai, J., Chen, X., Tan, T. (eds.) CCBR 2011. LNCS, vol. 7098, pp. 260–268. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-25449-9_33
Ren, H., Sun, L., Guo, J., Han, C.: A dataset and benchmark for multimodal biometric recognition based on fingerprint and finger vein. IEEE Trans. Inf. Foren. Secur. 17 (2022)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (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
Lv, W., Ma, H., Li, Y. (2022). A Finger Bimodal Fusion Algorithm Based on Improved Densenet. 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_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-20233-9_1
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)