Off-line signature verification using artificial immune recognition system

Author

Nemmour, Hassiba ; Chibani, Youcef

Author_Institution

Speech Commun. & Signal Process. Lab., Houari Boumediene Univ., Algiers, Algeria

fYear

2013

fDate

7-9 Nov. 2013

Firstpage

164

Lastpage

167

Abstract

In various pattern recognition applications, artificial immune systems achieve comparable and commonly higher performance than other classification schemes such as SVM. In this paper, we investigate their applicability for handwritten signature verification. Specifically, Ridgelet transform and grid features are used to extract pertinent characteristics. Performance assessment is conducted on the CEDAR dataset comparatively to SVM classifiers. The results in terms of average error rate highlight the high performance of artificial immune recognition algorithm.

Keywords

artificial immune systems; error statistics; feature extraction; handwriting recognition; pattern classification; support vector machines; transforms; CEDAR dataset; Ridgelet transform; SVM classifiers; artificial immune recognition algorithm; artificial immune recognition system; artificial immune systems; average error rate; classification schemes; feature extraction; grid features; handwritten signature verification; off-line signature verification; pattern recognition applications; performance assessment; Handwriting recognition; Immune system; Runtime; Support vector machines; Training; Transforms; Artificial immune system; Biometrics; Ridgelet transform; Signature verification; Support Vector Machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Computer and Computation (ICECCO), 2013 International Conference on

Conference_Location

Ankara

Type

conf

DOI

10.1109/ICECCO.2013.6718254

Filename

6718254