TELKOMNIKA (Telecommunication Computing Electronics and Control)
Vol 11, No 4: December 2013

Time Series Based for Online Signature Verification

Pande Sutawan (Udayana University)
Darma Putra (Udayana University)



Article Info

Publish Date
01 Dec 2013

Abstract

Signature verification system is to match the tested signature with a claimed signature. This paper propose time series based for feature extraction method and dynamic time warping for match method. The system made by process of testing 900 signatures belong to 50 participants, 3 signatures for reference and 5 signatures from original user, simple imposters and trained imposters for signatures test. The final result system was tested with 50 participants with 3 references. This test obtained that system accuracy without imposters is 90,45 % at threshold 44 with rejection errors (FNMR) is 5,2% and acceptance errors (FMR) is 4,35 %, when with imposters system accuracy is 80,13 % at threshold 27 with error rejection (FNMR) is 15,6% and acceptance errors (average FMR) is 4,26 %, with details as follows: acceptance errors is 0,39%, acceptance errors simple imposters is 3,2% and acceptance errors trained imposters is 9,2%.

Copyrights © 2013






Journal Info

Abbrev

TELKOMNIKA

Publisher

Subject

Computer Science & IT

Description

Submitted papers are evaluated by anonymous referees by single blind peer review for contribution, originality, relevance, and presentation. The Editor shall inform you of the results of the review as soon as possible, hopefully in 10 weeks. Please notice that because of the great number of ...