Online handwritten signature verification using neural network classifier based on principle component analysis

One of the main difficulties in designing online signature verification (OSV) system is to find the most distinctive features with high discriminating capabilities for the verification, particularly, with regard to the high variability which is inherent in genuine handwritten signatures, coupled wit...

Full description

Bibliographic Details
Main Authors: Iranmanesh, Vahab, Syed Ahmad Abdul Rahman, Sharifah Mumtazah, Wan Adnan, Wan Azizun, Yussof, Salman, Arigbabu, Olasimbo Ayodeji, Malallah, Fahad Layth
Format: Article
Language:English
Published: Hindawi Publishing Corporation 2014
Online Access:http://psasir.upm.edu.my/id/eprint/34746/
http://psasir.upm.edu.my/id/eprint/34746/1/Online%20Handwritten%20Signature%20Verification%20Using%20Neural.pdf
_version_ 1848847860041252864
author Iranmanesh, Vahab
Syed Ahmad Abdul Rahman, Sharifah Mumtazah
Wan Adnan, Wan Azizun
Yussof, Salman
Arigbabu, Olasimbo Ayodeji
Malallah, Fahad Layth
author_facet Iranmanesh, Vahab
Syed Ahmad Abdul Rahman, Sharifah Mumtazah
Wan Adnan, Wan Azizun
Yussof, Salman
Arigbabu, Olasimbo Ayodeji
Malallah, Fahad Layth
author_sort Iranmanesh, Vahab
building UPM Institutional Repository
collection Online Access
description One of the main difficulties in designing online signature verification (OSV) system is to find the most distinctive features with high discriminating capabilities for the verification, particularly, with regard to the high variability which is inherent in genuine handwritten signatures, coupled with the possibility of skilled forgeries having close resemblance to the original counterparts. In this paper, we proposed a systematic approach to online signature verification through the use of multilayer perceptron (MLP) on a subset of principal component analysis (PCA) features. The proposed approach illustrates a feature selection technique on the usually discarded information from PCA computation, which can be significant in attaining reduced error rates. The experiment is performed using 4000 signature samples from SIGMA database, which yielded a false acceptance rate (FAR) of 7.4% and a false rejection rate (FRR) of 6.4%.
first_indexed 2025-11-15T09:25:19Z
format Article
id upm-34746
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T09:25:19Z
publishDate 2014
publisher Hindawi Publishing Corporation
recordtype eprints
repository_type Digital Repository
spelling upm-347462015-12-21T14:06:24Z http://psasir.upm.edu.my/id/eprint/34746/ Online handwritten signature verification using neural network classifier based on principle component analysis Iranmanesh, Vahab Syed Ahmad Abdul Rahman, Sharifah Mumtazah Wan Adnan, Wan Azizun Yussof, Salman Arigbabu, Olasimbo Ayodeji Malallah, Fahad Layth One of the main difficulties in designing online signature verification (OSV) system is to find the most distinctive features with high discriminating capabilities for the verification, particularly, with regard to the high variability which is inherent in genuine handwritten signatures, coupled with the possibility of skilled forgeries having close resemblance to the original counterparts. In this paper, we proposed a systematic approach to online signature verification through the use of multilayer perceptron (MLP) on a subset of principal component analysis (PCA) features. The proposed approach illustrates a feature selection technique on the usually discarded information from PCA computation, which can be significant in attaining reduced error rates. The experiment is performed using 4000 signature samples from SIGMA database, which yielded a false acceptance rate (FAR) of 7.4% and a false rejection rate (FRR) of 6.4%. Hindawi Publishing Corporation 2014 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/34746/1/Online%20Handwritten%20Signature%20Verification%20Using%20Neural.pdf Iranmanesh, Vahab and Syed Ahmad Abdul Rahman, Sharifah Mumtazah and Wan Adnan, Wan Azizun and Yussof, Salman and Arigbabu, Olasimbo Ayodeji and Malallah, Fahad Layth (2014) Online handwritten signature verification using neural network classifier based on principle component analysis. The Scientific World Journal, 2014. art. no. 381469. pp. 1-8. ISSN 2356-6140; ESSN: 1537-744X http://www.hindawi.com/journals/tswj/2014/381469/abs/ 10.1155/2014/381469
spellingShingle Iranmanesh, Vahab
Syed Ahmad Abdul Rahman, Sharifah Mumtazah
Wan Adnan, Wan Azizun
Yussof, Salman
Arigbabu, Olasimbo Ayodeji
Malallah, Fahad Layth
Online handwritten signature verification using neural network classifier based on principle component analysis
title Online handwritten signature verification using neural network classifier based on principle component analysis
title_full Online handwritten signature verification using neural network classifier based on principle component analysis
title_fullStr Online handwritten signature verification using neural network classifier based on principle component analysis
title_full_unstemmed Online handwritten signature verification using neural network classifier based on principle component analysis
title_short Online handwritten signature verification using neural network classifier based on principle component analysis
title_sort online handwritten signature verification using neural network classifier based on principle component analysis
url http://psasir.upm.edu.my/id/eprint/34746/
http://psasir.upm.edu.my/id/eprint/34746/
http://psasir.upm.edu.my/id/eprint/34746/
http://psasir.upm.edu.my/id/eprint/34746/1/Online%20Handwritten%20Signature%20Verification%20Using%20Neural.pdf