Academic Journals Database
Disseminating quality controlled scientific knowledge

Time Series Based for Online Signature Verification

ADD TO MY LIST
 
Author(s): Pande Made Sutawan | A.A. Komping Oka Sudana | I Ketut Gede Darma Putra

Journal: TELKOMNIKA
ISSN 1693-6930

Volume: 11;
Issue: 4;
Date: 2013;
Original page

Keywords: Verification | Biometric | Time series | Online Signature

ABSTRACT
Signature verification system is to match the tested signature with a claimed signature. This paper proposes 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 90,44897959% at threshold 44 with rejection errors (FNMR) is 5,2% and acceptance errors (FMR) is 4,35102%, when with imposters system accuracy is 80,1361% at threshold 27 with error rejection (FNMR) is 15,6% and acceptance errors (average FMR) is 4,263946%, with details as follows: acceptance errors is 0,391837%, acceptance errors simple imposters is 3,2% and acceptance errors trained imposters is 9,2%.
Affiliate Program      Why do you need a reservation system?