DTW Based Classification of Diverse Pre-Processed Time Series Obtained from Handwritten PIN Words and Signatures
- 230 Downloads
- 3 Citations
Abstract
Personal identity verification by means of signature handwriting dynamics is a widely researched aspect of behavioral biometrics. The Dynamic Time Warping (DTW) technique has been successfully used for accessing the similarity of time series of handwritten objects by minimizing non-linear time distortions. Generally, in DTW based classifiers, the sequences are normalized in time and amplitude domains. In the paper, different length and amplitude normalization techniques are applied on signatures and handwritten PIN word sequences and their influence on accuracy of recognition are examined. A special approach to amplitude normalization based on reference level assigned Dynamic Time Warping (DTW) technique is presented. The standard deviation values calculated from the time series are used as so called bio-reference levels to improve the performance of classification. For this, they are added to the time series of query and sample datasets prior to DTW matching. The acquisition of online data is carried out by a digital pen equipped with pressure and inclination sensors. The time series obtained from the pen during handwriting provide valuable insight into the unique characteristics of the writers. Experimental results show that with the help of proposed length and amplitude normalizations of sequences including the bio-reference levels, the computational time is reduced and false acceptance rates are decreased.
Keywords
Biometric signature authentication Biometric person authentication Handwritten PIN recognition Dynamic time warping (DTW) Time series pre-processingNotes
Acknowledgment
The support given by G. Scharfenberg and BiSP team from the University of Applied Sciences Regensburg and of H.R. Kalbitzer from the University of Regensburg is highly acknowledged. We also want to thank the reviewers for their useful comments.
References
- 1.Impedovo, D., Modugno, R., Pirlo, G., & Stasolla, E. (2008). Handwritten signature verification by multiple reference set. In International Conference on Frontiers in Handwriting Recognition ICFHR.Google Scholar
- 2.Ningning, L., & Yunhong, W. (2008). Template selection for on-line signature verification. In IEEE, International Conference on Pattern Recognition, ICPR. Google Scholar
- 3.Keogh E. J., & Pazzani, M. J. (2000). Scaling up dynamic time warping for data mining applications. In Proceedings of the 6th International Conference on Knowledge Discovery and Data Mining. KDD.Google Scholar
- 4.Bashir, M., & Kempf, J. (2009). Reduced dynamic time warping for handwriting recognition based on multi-dimensional time series of a novel pen device. In International Journal of Computer Science, vol.4.3. Paris: WASET.Google Scholar
- 5.Bashir, M., & Kempf, J. (2009) Bio-inspired reference level assigned DTW for person identification using handwritten signatures. In BioID_MultiComm2009, LNCS 5707 (pp. 208–214). Springer-Verlag.Google Scholar
- 6.Fenton, D., Bouchard, M., & Yeap, T. H. (2006). Evaluation of features and normalization techniques for signature verification using dynamic timewarping. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP.Google Scholar
- 7.Zhang, J., & Kamata, S. (2008). Online signature verification using segment-to-segment matching. In International Conference on Frontiers in Handwriting Recognition, ICFHR.Google Scholar
- 8.Hao, F., & Wah, C. C. (2003). Online signature verification using a new extreme points warping technique. In Pattern Recognition Letter, vol.24, NY: Elsevier Science.Google Scholar
- 9.Bashir, M., & Kempf, J. (2009). Person authentication with RDTW using handwritten PIN and signature with a novel biometric smart pen device. In SSCI Computational Intelligence in Biometrics, IEEE, Nashville.Google Scholar
- 10.Keogh, E., & Ratanamahatana, C. A. (2004). Exact indexing of dynamic time warping. In Knowledge and Information Systems (pp. 358–386). London: Springer.Google Scholar
- 11.Henniger, O., & Muller, S. (2007). Effects of time normalization on the accuracy of dynamic time warping. In BTAS, 27–29, IEEE.Google Scholar
- 12.Ratanamahatana, C. A, & Keogh, E. (2005). Three myths about dynamic time warping data mining. In Proceedings of SIAM International Conference on Data Mining (SDM’05), (pp 506–510). Newport Beach, CA, April 21–23.Google Scholar
- 13.
- 14.Rath, T. M., & Manmatha, R. (2003) Lower-bounding of dynamic time warping distances for multivariate time Series. CIIR Technical Report MM-40.Google Scholar
- 15.Rath, T. M., & Manmatha, R. (2003). Word image matching using dynamic time warping. In Proc. of the Conf. on Computer Vision and Pattern Recognition (CVPR’03) IEEE, June. Multivariate Time Series. CIIR Technical Report MM-40.Google Scholar
- 16.Ji, H.-W., & Quan, Z.-H. (2005). Signature verification using wavelet transform and support vector machine. ICIC 2005, Part I, LNCS 3644 (pp. 671–678). Berlin Heidelberg: Springer-Verlag.Google Scholar
- 17.Gruber, C., Hook, C., Kempf, J., Scharfenberg, G., & Sick, B. (2006). A flexible architecture for online signature verification based on a novel biometric pen. In Proceedings of the 2006 IEEE Mountain Workshop on Adaptive and Learning Systems (SMCals/06) (pp. 110–115). Logan.Google Scholar
- 18.Isao, N., Hiroyuki, S., Yoshio, I., & Yutaka, F. (2005). Optimal user weighting fusion in DTW domain on-line signature verification. In LNCS 3546 (pp. 758–766).Google Scholar
- 19.Yeung, D. Y. et al. (2004). SVC2004: First international signature verification competition. In Int. Conf. on Biometric Authentication (ICBA) (pp. 16–22). Springer LNCS-3072. July 2004.Google Scholar