ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Off-line signature verification using genetically optimized weighted features

Ramesh, VE and Murty, Narasimha M (1999) Off-line signature verification using genetically optimized weighted features. In: Pattern Recognition, 32 (2). pp. 217-233.

[img] PDF
O¤-line_signature_veriÞcation.pdf - Published Version
Restricted to Registered users only

Download (448Kb) | Request a copy
Official URL: http://dx.doi.org/10.1016/S0031-3203(98)00141-1

Abstract

This paper is concerned with off-line signature verification. Four different types of pattern representation schemes have been implemented, viz., geometric features, moment-based representations, envelope characteristics and tree-structured Wavelet features. The individual feature components in a representation are weighed by their pattern characterization capability using Genetic Algorithms. The conclusions of the four subsystems teach depending on a representation scheme) are combined to form a final decision on the validity of signature. Threshold-based classifiers (including the traditional confidence-interval classifier), neighbourhood classifiers and their combinations were studied. Benefits of using forged signatures for training purposes have been assessed. Experimental results show that combination of the Feature-based classifiers increases verification accuracy. (C) 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

Item Type: Journal Article
Additional Information: Copyright of this article belongs to Elsevier Science.
Keywords: O¤-line signature veriÞcation;Genetic algorithms;Tree-structured wavelets;Threshold-based classiÞers; Neighbourhood classiÞers;Hybrid classiÞer;Combination of classiÞers
Department/Centre: Division of Electrical Sciences > Computer Science & Automation (Formerly, School of Automation)
Date Deposited: 29 Jun 2011 05:18
Last Modified: 29 Jun 2011 05:18
URI: http://eprints.iisc.ernet.in/id/eprint/38701

Actions (login required)

View Item View Item