Reference Hub5
Dynamic Structural Statistical Model Based Online Signature Verification

Dynamic Structural Statistical Model Based Online Signature Verification

Yan Chen, Xiaoqing Ding, Patrick S.P. Wang
Copyright: © 2009 |Volume: 1 |Issue: 3 |Pages: 21
ISSN: 1941-6210|EISSN: 1941-6229|ISSN: 1941-6210|EISBN13: 9781616920821|EISSN: 1941-6229|DOI: 10.4018/jdcf.2009070102
Cite Article Cite Article

MLA

Chen, Yan, et al. "Dynamic Structural Statistical Model Based Online Signature Verification." IJDCF vol.1, no.3 2009: pp.21-41. http://doi.org/10.4018/jdcf.2009070102

APA

Chen, Y., Ding, X., & Wang, P. S. (2009). Dynamic Structural Statistical Model Based Online Signature Verification. International Journal of Digital Crime and Forensics (IJDCF), 1(3), 21-41. http://doi.org/10.4018/jdcf.2009070102

Chicago

Chen, Yan, Xiaoqing Ding, and Patrick S.P. Wang. "Dynamic Structural Statistical Model Based Online Signature Verification," International Journal of Digital Crime and Forensics (IJDCF) 1, no.3: 21-41. http://doi.org/10.4018/jdcf.2009070102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In this article, a new dynamic structural statistical model based online signature verification algorithm is proposed, in which a method for statistical modeling the signature’s characteristic points is presented. Dynamic time warping is utilized to match two signature sequences so that correspondent characteristic point pair can be extracted from the matching result. Variations of a characteristic point are described by a multi-variable statistical probability distribution. Three methods for estimating the statistical distribution parameters are investigated. With this dynamic structural statistical model, a discriminant function can be derived to judges a signature to be genuine or forgery at the criterion of minimum potential risk. The proposed method takes advantage of both structure matching and statistical analysis. Tested in two signature databases, the proposed algorithm got much better signature verification performance than other results.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.