Improvement of japanese signature verification by segmentation-verification

Yuta Kamihira, Wataru Oyama, Tetsushi Wakabayashi, Fumitaka Kimura

Research output: Contribution to journalConference article

7 Citations (Scopus)

Abstract

This paper proposes a new combined signature verification technique called segmentation-verification based on three different off-line feature vectors extracted from full name Japanese signature image and from the sub-images of the first name and the last name. The Mahalanobis distance for each feature vector is calculated and the final decision (verification) is performed by SVM based on the three Mahalanobis distance. In the evaluation test the proposed technique achieved 94.30% verification accuracy, which is 1.03% higher than the best accuracy obtained from the full name signature image. This result shows that the proposed segmentation-verification approach improves Japanese signature verification accuracy significantly.

Original languageEnglish
Article number6628648
Pages (from-to)379-382
Number of pages4
JournalProceedings of the International Conference on Document Analysis and Recognition, ICDAR
DOIs
Publication statusPublished - Dec 11 2013
Event12th International Conference on Document Analysis and Recognition, ICDAR 2013 - Washington, DC, United States
Duration: Aug 25 2013Aug 28 2013

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Improvement of japanese signature verification by segmentation-verification. / Kamihira, Yuta; Oyama, Wataru; Wakabayashi, Tetsushi; Kimura, Fumitaka.

In: Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, 11.12.2013, p. 379-382.

Research output: Contribution to journalConference article

@article{3066ddc6bbc04b09a51ac1f3dcb024df,
title = "Improvement of japanese signature verification by segmentation-verification",
abstract = "This paper proposes a new combined signature verification technique called segmentation-verification based on three different off-line feature vectors extracted from full name Japanese signature image and from the sub-images of the first name and the last name. The Mahalanobis distance for each feature vector is calculated and the final decision (verification) is performed by SVM based on the three Mahalanobis distance. In the evaluation test the proposed technique achieved 94.30{\%} verification accuracy, which is 1.03{\%} higher than the best accuracy obtained from the full name signature image. This result shows that the proposed segmentation-verification approach improves Japanese signature verification accuracy significantly.",
author = "Yuta Kamihira and Wataru Oyama and Tetsushi Wakabayashi and Fumitaka Kimura",
year = "2013",
month = "12",
day = "11",
doi = "10.1109/ICDAR.2013.83",
language = "English",
pages = "379--382",
journal = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
issn = "1520-5363",

}

TY - JOUR

T1 - Improvement of japanese signature verification by segmentation-verification

AU - Kamihira, Yuta

AU - Oyama, Wataru

AU - Wakabayashi, Tetsushi

AU - Kimura, Fumitaka

PY - 2013/12/11

Y1 - 2013/12/11

N2 - This paper proposes a new combined signature verification technique called segmentation-verification based on three different off-line feature vectors extracted from full name Japanese signature image and from the sub-images of the first name and the last name. The Mahalanobis distance for each feature vector is calculated and the final decision (verification) is performed by SVM based on the three Mahalanobis distance. In the evaluation test the proposed technique achieved 94.30% verification accuracy, which is 1.03% higher than the best accuracy obtained from the full name signature image. This result shows that the proposed segmentation-verification approach improves Japanese signature verification accuracy significantly.

AB - This paper proposes a new combined signature verification technique called segmentation-verification based on three different off-line feature vectors extracted from full name Japanese signature image and from the sub-images of the first name and the last name. The Mahalanobis distance for each feature vector is calculated and the final decision (verification) is performed by SVM based on the three Mahalanobis distance. In the evaluation test the proposed technique achieved 94.30% verification accuracy, which is 1.03% higher than the best accuracy obtained from the full name signature image. This result shows that the proposed segmentation-verification approach improves Japanese signature verification accuracy significantly.

UR - http://www.scopus.com/inward/record.url?scp=84889607625&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84889607625&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2013.83

DO - 10.1109/ICDAR.2013.83

M3 - Conference article

AN - SCOPUS:84889607625

SP - 379

EP - 382

JO - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

JF - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

SN - 1520-5363

M1 - 6628648

ER -