A New Method of Signature Verification Based on Biomimetic Pattern Recognition Theory

Full Text (PDF, 167KB), PP.7-13

Views: 0 Downloads: 0

Author(s)

Yan Wu 1,* Hui Geng 1 Xiao-yue Bian 1

1. Department of Computer Science and Technology, Tongji University, Shanghai, China

* Corresponding author.

DOI: https://doi.org/10.5815/ijem.2011.03.02

Received: 17 Feb. 2011 / Revised: 25 Mar. 2011 / Accepted: 10 May 2011 / Published: 5 Jun. 2011

Index Terms

Signature verification, biomimetics pattern recognition, high-dimension space, super-sausage neuron

Abstract

Aim at the difficulty and low recognition rate of signature verification, this paper introduces biomimetic pattern recognition theory and applies it to the problem. According to the features of the signature samples, the coverage in the high-dimension feature space is built, one class of samples are all covered with a super-sausage neuron chain. As the radius selection of the super-sausage neurons maybe unreasonable, unwanted area may be covered and correct recognition rate will reduce. So this paper uses the relationship of the distance between the two training samples and the average distance of all the neurons to adjust the radius of the super-sausage neuron automatically. Finally, the experiments show that compared to traditional pattern recognition method, biomimetic pattern recognition theory used in signature verification have a better recognition result and is more effective.

Cite This Paper

Yan Wu,Hui Geng,Xiao-yue Bian,"A New Method of Signature Verification Based on Biomimetic Pattern Recognition Theory", IJEM, vol.1, no.3, pp.7-13, 2011. DOI: 10.5815/ijem.2011.03.02

Reference

[1]Luana Batista, Eric Granger, Robert Sabourin. A multi-hypothesis approach for off-line signature verification with HMMs[J]. 2009 10th International Conference on Document Analysis and Recognition, IEEE:13115-1319

[2]Diego Bertolini, Luiz S. Oliveira, Edson Justino, et al. Ensemble of classifiers for off-line signature verification [J]. 2008 IEEE International Conference on Systems, Man and Cybernetics (SMC 2008),IEEE:283-288

[3]Vu Nguyen, Michael Blumenstein, Vallipuram Muthukkumarasam, et al. Off-line signature verification using enhanced modified direction features in conjunction with neural classifiers and support vector machines. Ninth International Conference on Document Analysis and Recognition, IEEE, 2007, Vol.2(9):734-738

[4]Xiufen Ye, Weiping Hou, Weixing Feng. Off-line handwritten signature verification with inflections feature. International Conference on Mechatronics and Automation, Niagara Falls, Canada, IEEE, 2005.7:787-792

[5]Gang Chen, Bicheng Li, Jun Zhuang. Off-line handwritten signature verification based on moments and evidence theory[J] (in Chinese). Computer Applications, 2005, 18(18):57-60

[6]Cong Shen. Signature verification based on advanced multi_channel Gabor-wavelet transformation[D] (in Chinese).Master thesis, Beijing University of Technology, 2002

[7]Shoujue Wang. Biomimetic pattern recognition [J] (in Chinese), Acta Electronica Sinica,2002, 30(10):1417-1420

[8]Shoujue Wang. First step to multi-dimensional space biomimetic infomatics[M] (in Chinese).Beijing: National Defence Industry Press, 2008.1

[9]Bicheng Li, Tianqiang Peng, Bo Peng. Intelligent image processing[M] (in Chinese). Beijing:Electronic Industry Press, 2004