Based on EADTW On-Line Handwriting Signature Handwriting Signature Verification System Design and Implementation

Abstract:

In view of poor accuracy and slow calculation of the traditional on-line handwriting signature verification, an on-line handwriting signature verification based on Early Abandon Dynamic Time Warping (EADTW) was designed and implemented after numerous researched. The training template followed the mechanism of benchmark signature, while the certification part adopted EADTW algorithm. The experimental results showed that compared with on-line handwritten signature system based on DTW (dynamic time warping), this new system not only greatly reduced cumbersome and repeated calculation, but also obviously improved the accuracy, The bigger the test sample is, the more obvious the advantage is.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 5902-5905
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.5902
• Online since: May 2014
• Authors: Lei Ding*, Yong Jun Luo, Yang Yang Wang, Zheng Li, Bing Yin Yao
• Keywords: Benchmark Signature, EADTW, On-Line Handwritten, Signature Handwritten, Signature Verification

References

[1] Taherzadeh G, Karimi R, Ghobadi A, Beh HM. Evaluation of online signature verification features[C]. Advanced Communication Technology (ICACT), 2011 13th International Conference on, 2011, 772 – 777.

[2] Li Junkui, Wang Yuanzhen. Early Abandon to Accelerate Exactly Warping Machine of Time Series[C]. Journal of Computer Applications. 2010, 30(4) : 1068-1071.

DOI: 10.3724/sp.j.1087.2010.01068

[3] Li Junkui, Wang Yuanzhen, Li Haibo. A estimation method of time series similarity search in early termination efficiency [J]. Computer Science, 2009, 36(1): 114 - 117.

[4] Parizeau M, Plamondon R, A Comparative Analysis of Regional Correlation , Dynamic Time Warping and Skeletal Tree Matching for Matching for Signature Verification [C] . IEEE Trans on Pattern Analysis and Signature Verification [C]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1999, 12(7): 710-717.

DOI: 10.1109/34.56215

[5] Cunningham P, Carney J. Diversity versus quality in classification ensembles based on feature selection[M]. / / López de Mántaras R, Plaza E. LNCS: The 11th European Conference on Machine Learning. Heidelberg: Springer-Verlag, 2000: 109-116.

DOI: 10.1007/3-540-45164-1_12

[6] Ma Haibao, Liu Mandan, Zhang Cen. On-line handwritten signature verification method based on wavelet packet analysis[J]. Computer Engineering and Applications, 2007, 43 (12): 235-238.