Offline signature verification using geodesic derivative pattern

Samaneh Abdoli; Farshid Hajati

doi:10.1109/iraniancee.2014.6999685

Offline signature verification using geodesic derivative pattern

Samaneh Abdoli
, Farshid Hajati

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Citations (Scopus)

Abstract

In this paper, Geodesic Derivative Pattern (GDP) for Off-line handwritten signature verification is presented. We combine features based on both gray level and geometric information in the decision level. The Local Derivative Pattern (LDerivP) and the geodesic distance are used as features. It should be mention that the geodesic distance has never been used in offline signature verification. The method is tested on the GPDS960GraySignature database. Just one genuine sample per person has been used to train a KNN model and the remaining samples have been used for testing. Experimental evaluation demonstrates that the Geodesic Derivative Pattern (GDP) performs much better than the LDeriveP for offline signature verification.

Original language	English
Title of host publication	2014 22nd Iranian Conference on Electrical Engineering (ICEE)
Place of Publication	United States of America
Pages	1018-1023
DOIs	https://doi.org/10.1109/iraniancee.2014.6999685
Publication status	Published - 5 Jan 2015
Event	2014 22nd Iranian Conference on Electrical Engineering (ICEE) - Shahid Beheshti University, Tehran, Iran Duration: 20 May 2014 → 22 May 2014

Conference

Conference	2014 22nd Iranian Conference on Electrical Engineering (ICEE)
City	Tehran, Iran
Period	20/05/14 → 22/05/14

Access to Document

10.1109/iraniancee.2014.6999685

https://hdl.handle.net/1959.11/70774

Handle.net

Persistent link

Cite this

@inproceedings{ced291eefb7d45ba9653178201dd011b,

title = "Offline signature verification using geodesic derivative pattern",

abstract = "In this paper, Geodesic Derivative Pattern (GDP) for Off-line handwritten signature verification is presented. We combine features based on both gray level and geometric information in the decision level. The Local Derivative Pattern (LDerivP) and the geodesic distance are used as features. It should be mention that the geodesic distance has never been used in offline signature verification. The method is tested on the GPDS960GraySignature database. Just one genuine sample per person has been used to train a KNN model and the remaining samples have been used for testing. Experimental evaluation demonstrates that the Geodesic Derivative Pattern (GDP) performs much better than the LDeriveP for offline signature verification.",

author = "Samaneh Abdoli and Farshid Hajati",

year = "2015",

month = jan,

day = "5",

doi = "10.1109/iraniancee.2014.6999685",

language = "English",

isbn = "9781479944095",

pages = "1018--1023",

booktitle = "2014 22nd Iranian Conference on Electrical Engineering (ICEE)",

note = "2014 22nd Iranian Conference on Electrical Engineering (ICEE) ; Conference date: 20-05-2014 Through 22-05-2014",

}

TY - GEN

T1 - Offline signature verification using geodesic derivative pattern

AU - Abdoli, Samaneh

AU - Hajati, Farshid

PY - 2015/1/5

Y1 - 2015/1/5

N2 - In this paper, Geodesic Derivative Pattern (GDP) for Off-line handwritten signature verification is presented. We combine features based on both gray level and geometric information in the decision level. The Local Derivative Pattern (LDerivP) and the geodesic distance are used as features. It should be mention that the geodesic distance has never been used in offline signature verification. The method is tested on the GPDS960GraySignature database. Just one genuine sample per person has been used to train a KNN model and the remaining samples have been used for testing. Experimental evaluation demonstrates that the Geodesic Derivative Pattern (GDP) performs much better than the LDeriveP for offline signature verification.

AB - In this paper, Geodesic Derivative Pattern (GDP) for Off-line handwritten signature verification is presented. We combine features based on both gray level and geometric information in the decision level. The Local Derivative Pattern (LDerivP) and the geodesic distance are used as features. It should be mention that the geodesic distance has never been used in offline signature verification. The method is tested on the GPDS960GraySignature database. Just one genuine sample per person has been used to train a KNN model and the remaining samples have been used for testing. Experimental evaluation demonstrates that the Geodesic Derivative Pattern (GDP) performs much better than the LDeriveP for offline signature verification.

U2 - 10.1109/iraniancee.2014.6999685

DO - 10.1109/iraniancee.2014.6999685

M3 - Conference contribution

SN - 9781479944095

SP - 1018

EP - 1023

BT - 2014 22nd Iranian Conference on Electrical Engineering (ICEE)

CY - United States of America

T2 - 2014 22nd Iranian Conference on Electrical Engineering (ICEE)

Y2 - 20 May 2014 through 22 May 2014

ER -

Offline signature verification using geodesic derivative pattern

Abstract

Conference

Access to Document

Handle.net

Fingerprint

Cite this