Score level fusion approach in dynamic signature verification based on hybrid wavelet-Fourier transform

Wee How Khoh, Thian Song Ong, Ying Han Pang, Beng Jin Teoh

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

In this work, a dynamic handwritten signature verification system based on hybrid discrete wavelet transform and discrete Fourier transform is presented. Wavelet transform is adopted to analyze the signature information in a multi-resolution representation while retaining its local information by decomposing the signature into different sub-bands. Fourier transform is performed to extract the feature descriptor of the decomposed sub-bands. A dissimilarity score of the extracted features between the test signature and reference data is computed using Euclidean distance and enveloped Euclidean distance. Apart from that, several score level fusion mechanisms have been investigated to combine decisive information to boost up the system performance. The k-nearest neighbor and support vector machine are applied in order to fuse multiple features. The resulting score value is then normalized and compared with a threshold value in order to decide whether a given signature is genuine or forgery. Experiments are conducted on a released version of benchmark SVC2004 database. Two datasets (Task 1 and Task 2), which have different types of signature information, are used to evaluate the proposed system, and promising verification results are achieved.

Original languageEnglish
Pages (from-to)1067-1078
Number of pages12
JournalSecurity and Communication Networks
Volume7
Issue number7
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Wavelet transforms
Fourier transforms
Fusion reactions
Discrete wavelet transforms
Electric fuses
Discrete Fourier transforms
Support vector machines
Experiments

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Computer Networks and Communications

Cite this

@article{1175f3a724e74542aae5f1aecd4c7573,
title = "Score level fusion approach in dynamic signature verification based on hybrid wavelet-Fourier transform",
abstract = "In this work, a dynamic handwritten signature verification system based on hybrid discrete wavelet transform and discrete Fourier transform is presented. Wavelet transform is adopted to analyze the signature information in a multi-resolution representation while retaining its local information by decomposing the signature into different sub-bands. Fourier transform is performed to extract the feature descriptor of the decomposed sub-bands. A dissimilarity score of the extracted features between the test signature and reference data is computed using Euclidean distance and enveloped Euclidean distance. Apart from that, several score level fusion mechanisms have been investigated to combine decisive information to boost up the system performance. The k-nearest neighbor and support vector machine are applied in order to fuse multiple features. The resulting score value is then normalized and compared with a threshold value in order to decide whether a given signature is genuine or forgery. Experiments are conducted on a released version of benchmark SVC2004 database. Two datasets (Task 1 and Task 2), which have different types of signature information, are used to evaluate the proposed system, and promising verification results are achieved.",
author = "Khoh, {Wee How} and Ong, {Thian Song} and Pang, {Ying Han} and Teoh, {Beng Jin}",
year = "2014",
month = "1",
day = "1",
doi = "10.1002/sec.829",
language = "English",
volume = "7",
pages = "1067--1078",
journal = "Security and Communication Networks",
issn = "1939-0114",
publisher = "John Wiley and Sons Inc.",
number = "7",

}

Score level fusion approach in dynamic signature verification based on hybrid wavelet-Fourier transform. / Khoh, Wee How; Ong, Thian Song; Pang, Ying Han; Teoh, Beng Jin.

In: Security and Communication Networks, Vol. 7, No. 7, 01.01.2014, p. 1067-1078.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Score level fusion approach in dynamic signature verification based on hybrid wavelet-Fourier transform

AU - Khoh, Wee How

AU - Ong, Thian Song

AU - Pang, Ying Han

AU - Teoh, Beng Jin

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In this work, a dynamic handwritten signature verification system based on hybrid discrete wavelet transform and discrete Fourier transform is presented. Wavelet transform is adopted to analyze the signature information in a multi-resolution representation while retaining its local information by decomposing the signature into different sub-bands. Fourier transform is performed to extract the feature descriptor of the decomposed sub-bands. A dissimilarity score of the extracted features between the test signature and reference data is computed using Euclidean distance and enveloped Euclidean distance. Apart from that, several score level fusion mechanisms have been investigated to combine decisive information to boost up the system performance. The k-nearest neighbor and support vector machine are applied in order to fuse multiple features. The resulting score value is then normalized and compared with a threshold value in order to decide whether a given signature is genuine or forgery. Experiments are conducted on a released version of benchmark SVC2004 database. Two datasets (Task 1 and Task 2), which have different types of signature information, are used to evaluate the proposed system, and promising verification results are achieved.

AB - In this work, a dynamic handwritten signature verification system based on hybrid discrete wavelet transform and discrete Fourier transform is presented. Wavelet transform is adopted to analyze the signature information in a multi-resolution representation while retaining its local information by decomposing the signature into different sub-bands. Fourier transform is performed to extract the feature descriptor of the decomposed sub-bands. A dissimilarity score of the extracted features between the test signature and reference data is computed using Euclidean distance and enveloped Euclidean distance. Apart from that, several score level fusion mechanisms have been investigated to combine decisive information to boost up the system performance. The k-nearest neighbor and support vector machine are applied in order to fuse multiple features. The resulting score value is then normalized and compared with a threshold value in order to decide whether a given signature is genuine or forgery. Experiments are conducted on a released version of benchmark SVC2004 database. Two datasets (Task 1 and Task 2), which have different types of signature information, are used to evaluate the proposed system, and promising verification results are achieved.

UR - http://www.scopus.com/inward/record.url?scp=84902508062&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902508062&partnerID=8YFLogxK

U2 - 10.1002/sec.829

DO - 10.1002/sec.829

M3 - Article

AN - SCOPUS:84902508062

VL - 7

SP - 1067

EP - 1078

JO - Security and Communication Networks

JF - Security and Communication Networks

SN - 1939-0114

IS - 7

ER -