Human Signature Verification Using Machine Vision: Statistical and neural network approaches - Couverture souple

El-Faki, Mohammed; Al-Amoudi, Omer

 
9783330801547: Human Signature Verification Using Machine Vision: Statistical and neural network approaches
Couverture souple
ISBN 10 : 3330801549 ISBN 13 : 9783330801547
Editeur : Noor Publishing, 2016

Synopsis

Signature forgery still represents a great challenge to financial institutions, which makes accurate signature verification inevitable. On the other hand, computer technology and information processing areas witness remarkable qualitative improvements associated with significant costs reduction. This boosted the usage of machine vision techniques. In this research, an intensive work was carried out on offline signatures to establish a system for verifying them using their digital images. Signature morphological structure was utilized to explore characteristics associated with different signatures. Signature verification algorithms were developed using binary images of signatures employing two different verification approaches, one was based on statistical techniques, while the other was based on neural networks (NN) techniques. A signature database was built by collecting 840 signatures from 66 volunteers, and was used for training the statistical and NN classifiers and subsequently for testing purposes. Research results indicated that the statistical classifiers' outcomes were highly satisfactory whereas the NN classifiers' outcomes were not of the same quality.

Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.

Présentation de l'éditeur

Signature forgery still represents a great challenge to financial institutions, which makes accurate signature verification inevitable. On the other hand, computer technology and information processing areas witness remarkable qualitative improvements associated with significant costs reduction. This boosted the usage of machine vision techniques. In this research, an intensive work was carried out on offline signatures to establish a system for verifying them using their digital images. Signature morphological structure was utilized to explore characteristics associated with different signatures. Signature verification algorithms were developed using binary images of signatures employing two different verification approaches, one was based on statistical techniques, while the other was based on neural networks (NN) techniques. A signature database was built by collecting 840 signatures from 66 volunteers, and was used for training the statistical and NN classifiers and subsequently for testing purposes. Research results indicated that the statistical classifiers' outcomes were highly satisfactory whereas the NN classifiers' outcomes were not of the same quality.

Biographie de l'auteur

Mohammed S. El-Faki is a Prof. at King Faisal University. He got PhD. and MSc. from Kansas State University, and BSc. from Khartoum University. Research interests: pattern recognition, process automation, quality control, early detection of insects using mult-sensor fusion, water conservation, solar energy applications, date palm equipment design.

Les informations fournies dans la section « A propos du livre » peuvent faire référence à une autre édition de ce titre.

Éditeur
Noor Publishing
Date d'édition
2016
Langue
anglais
ISBN 10 
3330801549
ISBN 13 
9783330801547
Reliure
Broché
Nombre de pages
116
Coordonnées du fabricant
non disponible
Personne responsable
non disponible