Abstract
This paper proposes a multi-section vector quantization approach for on-line signature recognition. We have used a database of 330 users which includes 25 skilled forgeries performed by 5 different impostors. This database is larger than those typically used in the literature. Nevertheless, we also provide results from the SVC database. Our proposed system obtains similar results as the state-of-the-art online signature recognition algorithm, Dynamic Time Warping, with a reduced computational requirement, around 47 times lower. In addition, our system improves the database storage requirements due to vector compression, and is more privacy-friendly because it is not possible to recover the original signature using the codebooks. Experimental results reveal that our proposed multi-section vector quantization achieves a 98% identification rate, minimum Detection Cost Function value equal to 2.29% for random forgeries and 7.75% for skilled forgeries.
Similar content being viewed by others
References
Buck JT, Burton DK, Shore JE (1985) Text-dependent speaker recognition using vector quantization. IEEE ICASSP, pp 391–394
Burton DK, Shore JE, Buck JT (1983) A generalization of isolated word recognition using vector quantization. IEEE ICASSP, Boston, pp 1021–1024
Deller JR, Proakis JG, Hansen JHL (1987) Discrete-time processing of speech signals. Prentice Hall, Upper Saddle River
Faundez-Zanuy M (2004) On the vulnerability of biometric security systems. IEEE Aerosp Electr Syst Magaz 19(6):3–8
Faundez-Zanuy M (2005) Data fusion in biometrics. IEEE Aerosp Electr Syst Magaz 20(1):34–38
Faundez-Zanuy M (2005) Privacy issues on biometric systems. IEEE Aerosp Electr Syst Magaz 20(2):13–15
Faundez-Zanuy M (2005) Biometric recognition: why not massively adopted yet? IEEE Aerosp Electr Syst Magaz 20(8):25–28
Faundez-Zanuy M (2007) On-line signature recognition based on VQ-DTW. Pattern Recognition, vol 40. Elsevier, Amsterdam, pp 981–992
Faundez-Zanuy M, Monte-Moreno E (2005) State-of-the-art in speaker recognition. IEEE Aerosp Electr Syst Magaz 20(5):7–12
Gersho A, Gray RM (1991) Vector quantization and signal compression. Kluwer, Dordrecht
Guyon I, Makhoul J, Schwartz R, Vapnik V (1998) What size test set gives good error rate estimates? IEEE Trans Pattern Anal Mach Intell 20(1):52–64
Han K, Sethi IK (1996) Handwritten signature retrieval and identification. Pattern Recogn Lett 17:83–90
Higgins AL, Bahler LG, Porter JE (1993) Voice identification using nearest-neighbor distance measure. In: IEEE international conference on acoustics, speech and signal processing ICASSP, pp II-375, II-378
Houmani N et al (2009) BioSecure signature evaluation campaign 2009 (BSEC’2009). http://biometrics.it-sudparis.eu/BSEC2009/downloads/BSEC2009_results.pdf
Ortega-Garcia J, Gonzalez-Rodriguez J, Simon-Zorita D, Cruz-Llanas S (2002) From biometrics technology to applications regarding face, voice, signature and fingerprint recognition systems. Biometrics solutions for authentication in an E-World, Chap 12. Kluwer, Dordrecht
Jain A, Bolle R, Pankanti S (1999) Biometrics. Personal identification in a networked society. Kluwer, Dordrecht
Jain AK, Duin RPW, Mao J (2000) Statistical pattern recognition: a review. IEEE Trans Pattern Anal Mach Intell 22(1):4–37
Martin A et al (1997) The DET curve in assessment of detection performance. In: European speech processing conference Eurospeech, vol 4, pp 1895–1898
Nanavati S, Thieme M, Nanavati R, Biometrics (2002) Identity verification in a networked world. Wiley, New York
Nanni L, Lumini A (2006) Advanced methods for two-class problem formulation for on-line signature verification. Neurocomputing 69(7–9):854–857
Ortega-Garcia J, Fierrez J, Simon D, Gonzalez J, Faundez-Zanuy M, Espinosa V, Satue A, Hernaez I, Igarza J-J, Vivaracho C, Escudero D, Moro Q-I (2003) MCYT baseline corpus: a multimodal biometric database. IEE Proc Vision Image Signal Process 150:395–401
Plamondon R, Lorette G (1989) Automatic signature verification and writer identification- the state of the art. Pattern Recogn 1(2):107–131
Soong F, Rosenberg A, Rabiner L, Juang B (1985) A vector quantization approach to speaker recognition. IEEE Proc Int Conf Acoust Speech Signal Process 1:387–390 Tampa
Xiao X, Leedham G (2002) Signature verification using a modified Bayesian network. Pattern Recogn 35(5):983–995
Yeung D, Chang H, Xiong Y, George S, Kashi R, Matsumoto T, Rigoll G, (2004) SVC2004: first international signature verification competition. Lect Notes Comput Sci LNCS-3072, Springer, Berlin, pp 16–22
Zhang D (2000) Automated biometrics. Technologies and systems. Kluwer, Dordrecht
Acknowledgments
This work has been supported by FEDER and MEC, TEC2006-13141-C03-02/TCM, TEC2009-14123-C04-04.
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix 1: DTW algorithm
To find the optimal path to (i k , j k ) we simply take the minimum over all distance predecessors:
The simplest case corresponds to three predecessors.
The distance between a reference signature and a candidate’s signature can be computed using the following algorithm:
Best path has cost:
This notation is consistent with those provided in (Deller et al. 3). A complete explanation of this dynamic programming technique is beyond the scope of this paper.
Appendix 2: VQ algorithm
Given a distance measure between vectors i and j, such as, for instance, the euclidean distance:
The distance between a codebook and a candidate’s signature can be computed using the following algorithm:
Best match has cost \( \tilde{D} \)
Rights and permissions
About this article
Cite this article
Faundez-Zanuy, M., Pascual-Gaspar, J.M. Efficient on-line signature recognition based on multi-section vector quantization. Pattern Anal Applic 14, 37–45 (2011). https://doi.org/10.1007/s10044-010-0176-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-010-0176-8