Rapid off-line signature verification based on signature envelope and adaptive density partitioning

Vahid Malekian; Alireza Aghaei; Mahdie Rezaeian; Mahmood Alian

doi:10.1109/PRIA.2013.6528428

Rapid off-line signature verification based on signature envelope and adaptive density partitioning

Vahid Malekian, Alireza Aghaei, Mahdie Rezaeian, Mahmood Alian

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

5 Citations (Scopus)

Abstract

Handwritten signature is a widely used biometric which incorporates high intra personal variance. The most challenging problem in automatic signature verification is to extract features which are robust against this natural variability and at the same time discriminate between genuine and fake samples. This paper presents a novel method for extracting easily computed rotation and scale invariant features for offline signature verification. These features are extracted using the signature envelope and adaptive density partitioning. The effectiveness of the proposed features has been investigated over 900 signatures using a neural network classifier. The experimental results show the verification accuracy rate of 90.7%.

Original language	English
Title of host publication	2013 First Iranian Conference on Pattern Recognition and Image Analysis
Subtitle of host publication	PRIA 2013
Place of Publication	Piscataway, NJ
Pages	1-6
Number of pages	6
DOIs	https://doi.org/10.1109/PRIA.2013.6528428
Publication status	Published - 2013
Externally published	Yes
Event	1st Iranian Conference on Pattern Recognition and Image Analysis, PRIA 2013 - Birjand, Iran, Islamic Republic of Duration: 6 Mar 2013 → 8 Mar 2013

Other

Other	1st Iranian Conference on Pattern Recognition and Image Analysis, PRIA 2013
Country/Territory	Iran, Islamic Republic of
City	Birjand
Period	6/03/13 → 8/03/13

Keywords

Adaptive Density Partitioning
Artificial Neural Network (ANN)
Offline Signature Verification
Signature Envelope

Access to Document

10.1109/PRIA.2013.6528428

Cite this

@inproceedings{484c1f46208c47fc9523df83518115bc,

title = "Rapid off-line signature verification based on signature envelope and adaptive density partitioning",

abstract = "Handwritten signature is a widely used biometric which incorporates high intra personal variance. The most challenging problem in automatic signature verification is to extract features which are robust against this natural variability and at the same time discriminate between genuine and fake samples. This paper presents a novel method for extracting easily computed rotation and scale invariant features for offline signature verification. These features are extracted using the signature envelope and adaptive density partitioning. The effectiveness of the proposed features has been investigated over 900 signatures using a neural network classifier. The experimental results show the verification accuracy rate of 90.7%.",

keywords = "Adaptive Density Partitioning, Artificial Neural Network (ANN), Offline Signature Verification, Signature Envelope",

author = "Vahid Malekian and Alireza Aghaei and Mahdie Rezaeian and Mahmood Alian",

year = "2013",

doi = "10.1109/PRIA.2013.6528428",

language = "English",

isbn = "9781467362047",

pages = "1--6",

booktitle = "2013 First Iranian Conference on Pattern Recognition and Image Analysis",

note = "1st Iranian Conference on Pattern Recognition and Image Analysis, PRIA 2013 ; Conference date: 06-03-2013 Through 08-03-2013",

}

Malekian, V, Aghaei, A, Rezaeian, M & Alian, M 2013, Rapid off-line signature verification based on signature envelope and adaptive density partitioning. in 2013 First Iranian Conference on Pattern Recognition and Image Analysis: PRIA 2013., 6528428, Piscataway, NJ, pp. 1-6, 1st Iranian Conference on Pattern Recognition and Image Analysis, PRIA 2013, Birjand, Iran, Islamic Republic of, 6/03/13. https://doi.org/10.1109/PRIA.2013.6528428

Rapid off-line signature verification based on signature envelope and adaptive density partitioning. / Malekian, Vahid; Aghaei, Alireza; Rezaeian, Mahdie et al.
2013 First Iranian Conference on Pattern Recognition and Image Analysis: PRIA 2013. Piscataway, NJ, 2013. p. 1-6 6528428.

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

TY - GEN

T1 - Rapid off-line signature verification based on signature envelope and adaptive density partitioning

AU - Malekian, Vahid

AU - Aghaei, Alireza

AU - Rezaeian, Mahdie

AU - Alian, Mahmood

PY - 2013

Y1 - 2013

N2 - Handwritten signature is a widely used biometric which incorporates high intra personal variance. The most challenging problem in automatic signature verification is to extract features which are robust against this natural variability and at the same time discriminate between genuine and fake samples. This paper presents a novel method for extracting easily computed rotation and scale invariant features for offline signature verification. These features are extracted using the signature envelope and adaptive density partitioning. The effectiveness of the proposed features has been investigated over 900 signatures using a neural network classifier. The experimental results show the verification accuracy rate of 90.7%.

AB - Handwritten signature is a widely used biometric which incorporates high intra personal variance. The most challenging problem in automatic signature verification is to extract features which are robust against this natural variability and at the same time discriminate between genuine and fake samples. This paper presents a novel method for extracting easily computed rotation and scale invariant features for offline signature verification. These features are extracted using the signature envelope and adaptive density partitioning. The effectiveness of the proposed features has been investigated over 900 signatures using a neural network classifier. The experimental results show the verification accuracy rate of 90.7%.

KW - Adaptive Density Partitioning

KW - Artificial Neural Network (ANN)

KW - Offline Signature Verification

KW - Signature Envelope

UR - http://www.scopus.com/inward/record.url?scp=84881077930&partnerID=8YFLogxK

U2 - 10.1109/PRIA.2013.6528428

DO - 10.1109/PRIA.2013.6528428

M3 - Conference proceeding contribution

AN - SCOPUS:84881077930

SN - 9781467362047

SP - 1

EP - 6

BT - 2013 First Iranian Conference on Pattern Recognition and Image Analysis

CY - Piscataway, NJ

T2 - 1st Iranian Conference on Pattern Recognition and Image Analysis, PRIA 2013

Y2 - 6 March 2013 through 8 March 2013

ER -

Rapid off-line signature verification based on signature envelope and adaptive density partitioning

Abstract

Other

Keywords

Access to Document

Other files and links

Fingerprint

Cite this