OPTIMIZATION OF HIDDEN MARKOV MODEL PARAMETERS FOR BIOMETRIC SIGNATURE SYSTEMS
DOI:
https://doi.org/10.29121/shodhkosh.v3.i2.2022.6034Keywords:
Hidden, Parameters, (Hmms), Biometric, SignatureAbstract [English]
Hidden Markov Models (HMMs) have long been employed for biometric sequence modeling due to their robustness in capturing temporal dynamics. This paper presents a focused parametric analysis on how the selection of HMM parameters—specifically, the number of hidden states, observation symbols, and training samples—influences the Equal Error Rate (EER) in online signature verification systems. Using MATLAB simulations and the SVC 2004 dataset, we systematically vary these parameters while maintaining consistent preprocessing and feature extraction. Our findings highlight optimal parameter ranges that yield the best trade-off between model complexity and verification accuracy, with 4–5 hidden states and 300–350 observation symbols providing peak performance. These insights are intended to guide the design of efficient and accurate signature verification architectures.
References
Jain, A. K., et al. (2011). Introduction to Biometrics. Springer. DOI: https://doi.org/10.1007/978-0-387-77326-1
Impedovo, D., & Pirlo, G. (2008). Automatic Signature Verification: The State of the Art. IEEE Transactions on SMC. DOI: https://doi.org/10.1109/TSMCC.2008.923866
Galbally, J., Marcel, S., & Fierrez, J. (2015). Biometric Antispoofing Methods: A Survey. IEEE TIFS. DOI: https://doi.org/10.1109/ACCESS.2014.2381273
Rabiner, L. R. (1989). A Tutorial on Hidden Markov Models. IEEE Proceedings. DOI: https://doi.org/10.1109/5.18626
Starner, T., et al. (1998). Real-Time ASL Recognition Using HMMs. MIT Media Lab.
Justino, E., et al. (2005). Comparison of SVM and HMM in Signature Verification. Pattern Recognition Letters. DOI: https://doi.org/10.1016/j.patrec.2004.11.015
Yanikoglu, B., et al. (2005). Online Signature Verification with HMMs. PRL.
Revaud, J., et al. (2012). Temporal Encoding in Event Retrieval. CVPR.
Rattani, A., & Derakhshani, R. (2019). A Survey of Online Signature Verification. IEEE Access.
Zhang, Z., et al. (2022). Adaptive Symbol Clustering for HMM-Based Signature Verification. IEEE TBIOM.
Rantzsch, H., et al. (2020). Deep Learning for Signature Biometrics Using Siamese Networks. PRL.
Kekre, H. B., & Bharadi, V. A. (2014). Hybrid Wavelet Transform Using Orthogonal Pairs. IJCSIS.
Chavan, M., et al. (2017). Pressure-Based Feature Extraction for Online Signatures. ICCUBEA.
SVC 2004 Dataset. http://www.cse.ust.hk/svc2004/
Galbally, J., et al. (2020). Biometric Quality: Review and Applications. IEEE SPM.
Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.
Hassanat, A., & Jassim, S. (2022). Efficient HMM Estimation for Biometric Sequences. Expert Systems with Applications.
MacQueen, J. (1967). Some Methods for Classification and Analysis of Multivariate Observations.
Duda, R. O., et al. (2001). Pattern Classification. Wiley.
Bilmes, J. (1998). A Gentle Tutorial on the EM Algorithm and HMMs. UC Berkeley.
Gupta, P., & Gupta, S. (2020). Comparative Analysis of HMM and CNN for Signature Verification. IJCA.
Yilmaz, O., et al. (2021). Pressure Dynamics in Stylus-Based Writer Identification. Computers & Security.
Marzinotto, S., et al. (2011). Signature Biometrics on Mobile Devices. IEEE BTAS.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Dr. Vinayak A. Bharadi, and 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.
