SIGNATURE VERIFICATION USING LOW TRAINING SAMPLE REGIMES
DOI:
https://doi.org/10.29121/shodhkosh.v3.i2.2022.6032Abstract [English]
Signature verification systems often rely on a substantial number of user-enrolled samples to achieve high accuracy. However, real-world applications such as mobile banking and forensic verification often encounter constraints that limit the availability of training data. This study investigates the performance of a signature verification system trained with only 3 to 8 genuine signatures per user. Using the SVC 2004 dataset and hybrid wavelet transform (HWT)-based features, we analyze system behavior across different enrollment sizes and evaluate Equal Error Rate (EER), False Acceptance Rate (FAR), and False Rejection Rate (FRR). Results demonstrate that with optimized preprocessing and Hidden Markov Model (HMM) configurations, acceptable accuracy can be achieved even in low-sample regimes, with an EER of 5.1% using only 5 samples. These findings suggest that signature biometrics can be effectively deployed in limited-data scenarios.
References
Jain, A. K., Flynn, P., & Ross, A. A. (2011). Introduction to Biometrics. Springer. DOI: https://doi.org/10.1007/978-0-387-77326-1
Impedovo, D., & Pirlo, G. (2008). Automatic Signature Verification: State of the Art. IEEE Transactions on Systems, Man, and Cybernetics. DOI: https://doi.org/10.1109/TSMCC.2008.923866
Galbally, J., Marcel, S., & Fierrez, J. (2015). Biometric Antispoofing Methods: A Survey in Face, Iris, and Fingerprint Modalities. IEEE Transactions on Information Forensics and Security. DOI: https://doi.org/10.1109/ACCESS.2014.2381273
Rattani, A., & Derakhshani, R. (2019). A Survey of Online Signature Verification. IEEE Access.
Ferrer, M. A., Galbally, J., & Alonso-Fernandez, F. (2020). Exploiting Explainable AI Techniques for Online Signature Verification. Pattern Recognition Letters.
Hassanat, A. B. A., & Jassim, S. A. (2022). A Review of Biometric Authentication Systems Using Hidden Markov Models. Expert Systems with Applications.
Kisku, D. R., & Rattani, A. (2021). Biometric Recognition: Challenges and Solutions for Lightweight Models. Springer.
Chavan, M., et al. (2017). Pressure-Driven Feature Selection in Signatures. In Proceedings of ICCUBEA.
Kekre, H. B., & Bharadi, V. A. (2014). Hybrid Wavelet Transform Construction Using Two Orthogonal Transforms. International Journal of Computer Science and Information Security.
SVC 2004 Signature Dataset. http://www.cse.ust.hk/svc2004/
Yilmaz, O., et al. (2020). Improving Signature Verification with Deep Pressure Features. Computers & Security.
Bharadi, V., & Chavan, M. (2015). HWT Feature Vector Generation for Signature Verification. In IEEE Confluence.
Rabiner, L. R. (1989). A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE. DOI: https://doi.org/10.1016/B978-0-08-051584-7.50027-9
Revaud, J., Douze, M., Schmid, C., & Jegou, H. (2012). Event Retrieval in Video Using Signature Descriptors. In CVPR.
Rantzsch, H., et al. (2020). Deep Learning-Based Signature Verification Using Siamese Networks. Pattern Recognition Letters.
Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.
Bilmes, J. (1998). A Gentle Tutorial on the EM Algorithm and its Application to HMMs. University of California, Berkeley.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Dr. Vinayak A. Bharadi, Dr. Manoj Chavan
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
