Multimodal Biometric Authentication Based On Finger Vein And Fingerprint Recognition Using Artificial Intelligence
DOI:
https://doi.org/10.29284/7afcv793Keywords:
Multimodal Biometric Authentication, Finger Vein, Fingerprint Recognition, Artificial Intelligence.Abstract
As of now, the majority of multimodal biometric systems that utilize multiple modalities for biometric authentication utilize different approaches to train and tune deep learning models to obtain improved performance through training or fine-tuning the model to improve their performance. Many of these techniques can provide a high level of accuracy, but they also add high levels of computational complexity to the system, thus they may not work well in an environment that has limited training data available. The purpose of this study is to introduce a multimodal biometric authentication framework based on the use of pre-trained deep learning models to extract features from multiple modalities without using additional training or tuning to obtain the feature set. More specifically, the study uses VGG16, EfficientNetB0, and ResNet50 as feature extraction methods. In addition, an attention mechanism will be used to increase the effectiveness of the most informative features and will then be reduced by using Principal Component Analysis (PCA) while preserving 95% of the variance. K-Nearest Neighbors (KNN) will be used to classify the reduced features for finger vein recognition, while Random Forest will be used to classify the reduced features of fingerprint recognition. The experimental framework was developed using the Python programming language, and the results were 98.3% recognition accuracy for finger vein and 98.9% recognition accuracy for fingerprint. Finally, the fingerprint and finger vein modalities were fused at the decision level for highly accurate authentication performance. The proposed method shows that high accuracy of recognition can be obtained with low computational complexity using lightweight and interpretable techniques.
References
[1] A. Ross and A. K. Jain, “Multimodal biometrics: An overview,” in Proc. 12th European Signal Processing Conference (EUSIPCO), 2004.
[2] A. K. Jain, P. Flynn, and A. A. Ross, Handbook of Biometrics. New York, NY, USA: Springer, 2007.
[3] N. K. Ratha, J. H. Connell, and R. M. Bolle, “An analysis of minutiae matching strength,” in Audio- and Video-Based Biometric Person Authentication. Springer, 2001.
[4] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105, 2012.
[5] Y. Bengio, A. Courville, and P. Vincent, “Representation learning: A review and new perspectives,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 35, no. 8, pp. 1798–1828, 2013.
[6] C. Shorten and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Journal of Big Data, vol. 6, no. 1, p. 60, 2019.
[7] R. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, and R. X. Gao, “Deep learning and its applications to machine health monitoring,” Mechanical Systems and Signal Processing, vol. 115, pp. 213–237, 2019.
[8] F. Doshi-Velez and B. Kim, “Towards a rigorous science of interpretable machine learning,” arXiv preprint arXiv:1702.08608, 2017.
[9] Q. Zhang and S. C. Zhu, “Visual interpretability for deep learning: A survey,” arXiv preprint arXiv:1802.00614, 2018.
[10] K. Zuiderveld, “Contrast-limited adaptive histogram equalization,” in Graphics Gems IV. Academic Press, 1994.
[11] R. Maini and H. Aggarwal, “A comprehensive review of image enhancement techniques,” arXiv preprint arXiv:1003.4053, 2010.
[12] S. Almuwayziri et al., “Deep learning-based fingerprint–vein biometric fusion: A systematic review with empirical evaluation,” Applied Sciences, vol. 15, no. 15, p. 8502, 2025.
[13] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
[14] J. Shen, X. Ding, Y. Wang, et al., “Finger vein recognition algorithm based on lightweight deep convolutional neural network,” IEEE Trans. Instrumentation and Measurement, vol. 71, pp. 1–13, 2021.
[15] S. Woo, J. Park, J. Y. Lee, and I. S. Kweon, “CBAM: Convolutional block attention module,” in Proc. European Conference on Computer Vision (ECCV), 2018.
[16] S. Jetley, N. A. Lord, N. Lee, and P. H. S. Torr, “Learn to pay attention,” arXiv preprint arXiv:1804.02391, 2018.
[17] I. T. Jolliffe, “Principal component analysis,” in Encyclopedia of Statistics in Behavioral Science, 2005.
[18] X. Wang, R. Girshick, A. Gupta, and K. He, “Non-local neural networks,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2018.
[19] L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
[20] T. Cover and P. Hart, “Nearest neighbor pattern classification,” IEEE Trans. Information Theory, vol. 13, no. 1, pp. 21–27, 1967.
[21] R. P. W. Duin et al., “On combining classifiers,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 3, pp. 226–239, 1998.
[22] A. Ross and A. K. Jain, “Information fusion in biometrics,” Pattern Recognition Letters, vol. 24, no. 13, pp. 2115–2125, 2003.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
