Combination of signature verification techniques by SVM

Takashi Ito, Wataru Oyama, Tetsushi Wakabayashi, Fumitaka Kimura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

This paper proposes a new SVM based technique for combining signature verification techniques using off-line features and on-line features. The off-line feature based technique employs gradient feature vector representing the shape of signature image, and the on-line feature based technique employs dynamic programming (DP) matching technique for time series data of the signatures. The final decision (verification) is performed by SVM based on output from those off-line and online techniques. In the evaluation test the proposed technique achieved 92.96% verification accuracy, which is 1.4% higher than the better accuracy obtained by the individual techniques. This result shows that combining multiple techniques by SVM improves signature verification accuracy significantly.

Original languageEnglish
Title of host publicationProceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012
Pages430-433
Number of pages4
DOIs
Publication statusPublished - Dec 1 2012
Externally publishedYes
Event13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012 - Bari, Italy
Duration: Sep 18 2012Sep 20 2012

Other

Other13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012
CountryItaly
CityBari
Period9/18/129/20/12

Fingerprint

Dynamic programming
Time series

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Ito, T., Oyama, W., Wakabayashi, T., & Kimura, F. (2012). Combination of signature verification techniques by SVM. In Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012 (pp. 430-433). [6424431] https://doi.org/10.1109/ICFHR.2012.192

Combination of signature verification techniques by SVM. / Ito, Takashi; Oyama, Wataru; Wakabayashi, Tetsushi; Kimura, Fumitaka.

Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012. 2012. p. 430-433 6424431.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ito, T, Oyama, W, Wakabayashi, T & Kimura, F 2012, Combination of signature verification techniques by SVM. in Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012., 6424431, pp. 430-433, 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012, Bari, Italy, 9/18/12. https://doi.org/10.1109/ICFHR.2012.192
Ito T, Oyama W, Wakabayashi T, Kimura F. Combination of signature verification techniques by SVM. In Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012. 2012. p. 430-433. 6424431 https://doi.org/10.1109/ICFHR.2012.192
Ito, Takashi ; Oyama, Wataru ; Wakabayashi, Tetsushi ; Kimura, Fumitaka. / Combination of signature verification techniques by SVM. Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012. 2012. pp. 430-433
@inproceedings{317fdba2d5134db6b123f04ef9de3093,
title = "Combination of signature verification techniques by SVM",
abstract = "This paper proposes a new SVM based technique for combining signature verification techniques using off-line features and on-line features. The off-line feature based technique employs gradient feature vector representing the shape of signature image, and the on-line feature based technique employs dynamic programming (DP) matching technique for time series data of the signatures. The final decision (verification) is performed by SVM based on output from those off-line and online techniques. In the evaluation test the proposed technique achieved 92.96{\%} verification accuracy, which is 1.4{\%} higher than the better accuracy obtained by the individual techniques. This result shows that combining multiple techniques by SVM improves signature verification accuracy significantly.",
author = "Takashi Ito and Wataru Oyama and Tetsushi Wakabayashi and Fumitaka Kimura",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/ICFHR.2012.192",
language = "English",
isbn = "9780769547749",
pages = "430--433",
booktitle = "Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012",

}

TY - GEN

T1 - Combination of signature verification techniques by SVM

AU - Ito, Takashi

AU - Oyama, Wataru

AU - Wakabayashi, Tetsushi

AU - Kimura, Fumitaka

PY - 2012/12/1

Y1 - 2012/12/1

N2 - This paper proposes a new SVM based technique for combining signature verification techniques using off-line features and on-line features. The off-line feature based technique employs gradient feature vector representing the shape of signature image, and the on-line feature based technique employs dynamic programming (DP) matching technique for time series data of the signatures. The final decision (verification) is performed by SVM based on output from those off-line and online techniques. In the evaluation test the proposed technique achieved 92.96% verification accuracy, which is 1.4% higher than the better accuracy obtained by the individual techniques. This result shows that combining multiple techniques by SVM improves signature verification accuracy significantly.

AB - This paper proposes a new SVM based technique for combining signature verification techniques using off-line features and on-line features. The off-line feature based technique employs gradient feature vector representing the shape of signature image, and the on-line feature based technique employs dynamic programming (DP) matching technique for time series data of the signatures. The final decision (verification) is performed by SVM based on output from those off-line and online techniques. In the evaluation test the proposed technique achieved 92.96% verification accuracy, which is 1.4% higher than the better accuracy obtained by the individual techniques. This result shows that combining multiple techniques by SVM improves signature verification accuracy significantly.

UR - http://www.scopus.com/inward/record.url?scp=84874239667&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874239667&partnerID=8YFLogxK

U2 - 10.1109/ICFHR.2012.192

DO - 10.1109/ICFHR.2012.192

M3 - Conference contribution

AN - SCOPUS:84874239667

SN - 9780769547749

SP - 430

EP - 433

BT - Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012

ER -