Time Series Based for Online Signature Verification
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%.
Author: Pande Sutawan, Darma
Putra
Journal Code: jptkomputergg130105
