Off-line text-independent writer identification using a mixture of global and local features

Yiu Ming CHEUNG; Junping Deng

doi:10.1109/CIS.2011.340

Off-line text-independent writer identification using a mixture of global and local features

Yiu Ming CHEUNG^*, Junping Deng

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

3 Citations (Scopus)

Abstract

The existing works on writer identification consider global feature or local feature, respectively, but not both. Actually, both of global and local features provide the useful information for writer identification. Hence, this paper proposes a method for writer identification by using a mixture of global feature and local feature. In implementation, we utilize 2-D Gabor transformation as the global feature and Local Binary Pattern (LBP) as the local feature for writer identification. The experiment results show that the combination of global and local feature outperforms the utilization of each single one.

Original language	English
Title of host publication	Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011
Pages	1524-1527
Number of pages	4
DOIs	https://doi.org/10.1109/CIS.2011.340
Publication status	Published - 2011
Event	2011 7th International Conference on Computational Intelligence and Security, CIS 2011 - Sanya, Hainan, China Duration: 3 Dec 2011 → 4 Dec 2011

Publication series

Name	Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011

Conference

Conference	2011 7th International Conference on Computational Intelligence and Security, CIS 2011
Country/Territory	China
City	Sanya, Hainan
Period	3/12/11 → 4/12/11

Scopus Subject Areas

Artificial Intelligence
Computational Theory and Mathematics

User-Defined Keywords

2-D Gabor
LBP
Mixture of features
Writer identification

Access to Document

10.1109/CIS.2011.340

Cite this

CHEUNG, Y. M., & Deng, J. (2011). Off-line text-independent writer identification using a mixture of global and local features. In Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011 (pp. 1524-1527). Article 6128381 (Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011). https://doi.org/10.1109/CIS.2011.340

@inproceedings{4fb8a95d4c464da79454e42f3d99a0f2,

title = "Off-line text-independent writer identification using a mixture of global and local features",

abstract = "The existing works on writer identification consider global feature or local feature, respectively, but not both. Actually, both of global and local features provide the useful information for writer identification. Hence, this paper proposes a method for writer identification by using a mixture of global feature and local feature. In implementation, we utilize 2-D Gabor transformation as the global feature and Local Binary Pattern (LBP) as the local feature for writer identification. The experiment results show that the combination of global and local feature outperforms the utilization of each single one.",

keywords = "2-D Gabor, LBP, Mixture of features, Writer identification",

author = "CHEUNG, {Yiu Ming} and Junping Deng",

year = "2011",

doi = "10.1109/CIS.2011.340",

language = "English",

isbn = "9780769545844",

series = "Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011",

pages = "1524--1527",

booktitle = "Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011",

note = "2011 7th International Conference on Computational Intelligence and Security, CIS 2011 ; Conference date: 03-12-2011 Through 04-12-2011",

}

CHEUNG, YM & Deng, J 2011, Off-line text-independent writer identification using a mixture of global and local features. in Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011., 6128381, Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011, pp. 1524-1527, 2011 7th International Conference on Computational Intelligence and Security, CIS 2011, Sanya, Hainan, China, 3/12/11. https://doi.org/10.1109/CIS.2011.340

Off-line text-independent writer identification using a mixture of global and local features. / CHEUNG, Yiu Ming; Deng, Junping.
Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011. 2011. p. 1524-1527 6128381 (Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Off-line text-independent writer identification using a mixture of global and local features

AU - CHEUNG, Yiu Ming

AU - Deng, Junping

PY - 2011

Y1 - 2011

N2 - The existing works on writer identification consider global feature or local feature, respectively, but not both. Actually, both of global and local features provide the useful information for writer identification. Hence, this paper proposes a method for writer identification by using a mixture of global feature and local feature. In implementation, we utilize 2-D Gabor transformation as the global feature and Local Binary Pattern (LBP) as the local feature for writer identification. The experiment results show that the combination of global and local feature outperforms the utilization of each single one.

AB - The existing works on writer identification consider global feature or local feature, respectively, but not both. Actually, both of global and local features provide the useful information for writer identification. Hence, this paper proposes a method for writer identification by using a mixture of global feature and local feature. In implementation, we utilize 2-D Gabor transformation as the global feature and Local Binary Pattern (LBP) as the local feature for writer identification. The experiment results show that the combination of global and local feature outperforms the utilization of each single one.

KW - 2-D Gabor

KW - LBP

KW - Mixture of features

KW - Writer identification

UR - http://www.scopus.com/inward/record.url?scp=84856552236&partnerID=8YFLogxK

U2 - 10.1109/CIS.2011.340

DO - 10.1109/CIS.2011.340

M3 - Conference proceeding

AN - SCOPUS:84856552236

SN - 9780769545844

T3 - Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011

SP - 1524

EP - 1527

BT - Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011

T2 - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011

Y2 - 3 December 2011 through 4 December 2011

ER -

CHEUNG YM, Deng J. Off-line text-independent writer identification using a mixture of global and local features. In Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011. 2011. p. 1524-1527. 6128381. (Proceedings - 2011 7th International Conference on Computational Intelligence and Security, CIS 2011). doi: 10.1109/CIS.2011.340

Off-line text-independent writer identification using a mixture of global and local features

Abstract

Publication series

Conference

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this