Abstract
Multimodal graph fusion utilizes the modeling of weighted graph to combine information from multiple sources in order to improve recognition performance whilst addressing some limitations of traditional methods. In this work, we propose a novel approach for the finger trimodal graph fusion, by extending the crystal-like bijective structure to the Atomic Group-like heterostructure. The crucial aspect is to establish the inter-modal correlation. Inspired by chemical bonds, we construct atom serial numbers by pre-clustering the divided image blocks in one modality. Then, we trained a node classifier to share the set of serial numbers among the three modalities. As a result, nodes across modalities can be bonded. Furthermore, both the feature attributes and position information are taken into consideration for the intra-modal edges of the fused graph. Finally, we design heterogeneous graphs with higher recognition potential. Experimental results show that with our strategy, we can improve matching accuracy to 96.6% while lowering the equal error rate to 2.687%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Jain, A.K., Ross, A.: Multibiometric systems. Commun. ACM 47(1), 34–40 (2004)
Khellat-Kihel, S., Abrishambaf, R., Monteiro, J.L., Benyettou, M.: Multimodal fusion of the finger vein, fingerprint and the finger-knuckle-print using Kernel Fisher analysis. Appl. Soft Comput. 42, 439–447 (2016)
Jain, A.K., Ross, A., Prabhakar, S.: An introduction to biometric recognition. IEEE Trans. Circuits Syst. Video Technol. 14(1), 4–20 (2004)
Zhang, H., Li, S., Shi, Y., Yang, J.: Graph fusion for finger multimodal biometrics. IEEE Access 7, 28607–28615 (2019)
Foggia, P., Percannella, G., Vento, M.: Graph matching and learning in pattern recognition in the last 10 years. Int. J. Pattern Recognit. Artif. Intell. 28(01), 1450001 (2014)
Chen, J., Pan, L., Wei, Z., Wang, X., Ngo, C., Chua, T.: Zero-shot ingredient recognition by multi-relational graph convolutional network. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 10542–10550 (2020)
Choi, G., Lim, C., Choi, H.: A center-biased graph learning algorithm for image classification. In: 2017 IEEE International Conference on Big Data and Smart Computing (BigComp), pp. 324–327. IEEE (2017)
Luo, B., Wilson, R.C., Hancock, E.R.: Spectral embedding of graphs. Pattern Recogn. 36(10), 2213–2230 (2003)
Li, S., Zhang, B., Fei, L., Zhao, S.: Joint discriminative feature learning for multi-modal finger recognition. Pattern Recogn. 111, 107704 (2021)
Zhao, J., Ai, D., Huang, Y., Song, H., Wang, Y., Yang, J.: Quantitation of vascular morphology by directed graph construction. IEEE Access 7, 21609–21622 (2019)
Arakala, A., Davis, S.A., Hao, H., Horadam, K.J.: Value of graph topology in vascular biometrics. IET Biometrics 6(2), 117–125 (2017)
Nayar, G.R., Thomas, T., Emmanuel, S.: Graph based secure cancelable palm vein biometrics. J. Inf. Secur. Appl. 62, 102991 (2021)
Ye, Z., Yang, J.: A finger-vein recognition method based on weighted graph model. J. Shandong Univ. (Eng. Sci.) 48(3), 103–109 (2018)
Simoncelli, E.P., Farid, H.: Steerable wedge filters for local orientation analysis. IEEE Trans. Image Process. 5(9), 1377–1382 (1996)
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
Li, Q., Han, Z., Wu, X.: Deeper insights into graph convolutional networks for semi-supervised learning. In: Thirty-Second AAAI Conference on Artificial Intelligence, Louisiana, USA, pp. 3538–3545 (2018)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations, Toulon, France. PMLR (2016)
Li, Y., Gu, C., Dullien, T., Vinyals, O., Kohli, P.: Graph matching networks for learning the similarity of graph structured objects. In: International Conference on Machine Learning, California, USA, pp. 3835–3845. PMLR (2019)
Nikolentzos, G., Vazirgiannis, M.: Random walk graph neural networks. Adv. Neural. Inf. Process. Syst. 33, 16211–16222 (2020)
Bai, Y., Ding, H., Bian, S., Chen, T., Sun, Y., Wang, W.: SimGNN: a neural network approach to fast graph similarity computation. In: Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, Melbourne VIC, Australia, pp. 384–392. Association for Computing Machinery (2019)
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
Wang, Y., Zhang, W., Yang, J. (2022). Heterogeneous Graph-Based Finger Trimodal Fusion. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13534. Springer, Cham. https://doi.org/10.1007/978-3-031-18907-4_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-18907-4_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18906-7
Online ISBN: 978-3-031-18907-4
eBook Packages: Computer ScienceComputer Science (R0)