Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
381532 | Engineering Applications of Artificial Intelligence | 2009 | 7 Pages |
Abstract
Analysis of signature is a widely used and developed area of research for personal verification. A typical signature verification (SV) system generally consists of four components: data acquisition, pre-processing, feature extraction and verification. A reliable SV toolbox, based on the verification of off-line signatures is developed with the proposed algorithm. The technique is based on a neural network (NN) approach trained with particle swarm optimization (PSO) algorithm. To test the performance of the proposed PSO-NN algorithm two types of forgeries—unskilled and skilled—are examined. The experimental results are illustrated on the selected signature databases and presented herein.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
M. Taylan Das, L. Canan Dulger,