A new online signature verification algorithm using variable length segmentation and hidden Markov models

Author

Shafiei, Mohammad M. ; Rabiee, Hamid R.

Author_Institution

Digital Media Lab, Sharif Univ. of Technol., Tehran, Iran

fYear

2003

fDate

3-6 Aug. 2003

Firstpage

443

Abstract

In this paper, a new on-line handwritten signature verification system using Hidden Markov Model (HMM) is presented. The proposed system segments each signature based on its perceptually important points and then computes for each segment a number of features that are scale and displacement invariant. The resulted sequence is then used for training an HMM to achieve signature verification. Our database includes 622 genuine signatures and 1010 forgery signatures that were collected from a population of 69 human subjects. Our verification system has achieved a false acceptance rate (FAR) of 4% and a false rejection rate (FRR) of 12%.

Keywords

algorithm theory; authorisation; error statistics; financial data processing; handwriting recognition; hidden Markov models; image segmentation; online front-ends; variable length codes; HMM; biometric authentication; displacement invariant features; false acceptance; false rejection; financial transactions; hidden Markov models; online signature verification algorithm; public acceptance; scale invariant features; signature segmentation; variable length segmentation; Authentication; Biometrics; Feature extraction; Fingerprint recognition; Forgery; Handwriting recognition; Hidden Markov models; Humans; Spatial databases; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 2003. Proceedings. Seventh International Conference on

Print_ISBN

0-7695-1960-1

Type

conf

DOI

10.1109/ICDAR.2003.1227706

Filename

1227706