Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/44053
Title: Off-line signature verification based on gray level information using wavelet transform and texture features
Authors: Vargas, J. F.
Travieso, C. M. 
Alonso, J. B. 
Ferrer, M. A. 
UNESCO Clasification: 3307 Tecnología electrónica
Keywords: Forgery , Wavelet transforms , Wavelet analysis , Databases , Training , Matrix decomposition , Kernel
Issue Date: 2010
Journal: Proceedings - 12th International Conference on Frontiers in Handwriting Recognition, ICFHR 2010
Conference: 12th International Conference on Frontiers in Handwriting Recognition, ICFHR 2010 
Abstract: A method for Off-line Handwritten Signature Verification is described. It works at the global and local image level, measuring the stroke gray-level variations by means of wavelet analysys and statistical texture features. This method begins with a proposed background removal. Then Wavelet Analysis allows to estimate and alleviate the global influence of ink-type, and finally, properties of the Co-occurrence Matrix are used as features representing individual characteristics at local level. Genuine samples have been used for train an SVM model, random and skilled forgeries have been used for testing it. Experiments were conducted on three differente databases (MCYT75, GPDS100, and GPDS750). Results are reasonable according to the state of the art and approaches that use the same public available database (MCYT75) and prove the feasibility of the proposed methodology.
URI: http://hdl.handle.net/10553/44053
ISBN: 9780769542218
DOI: 10.1109/ICFHR.2010.96
Source: Proceedings - 12th International Conference on Frontiers in Handwriting Recognition, ICFHR 2010 (5693627), p. 587-592
Appears in Collections:Actas de congresos
Show full item record

SCOPUSTM   
Citations

20
checked on Feb 28, 2021

Page view(s)

27
checked on Mar 1, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.