A hybrid HMM/ANN based approach for online signature verification

Zhong Hua Quan; De Shuang Huang; Kun Hong Liu; Kwok Wing Chau

doi:10.1109/IJCNN.2007.4370990

A hybrid HMM/ANN based approach for online signature verification

Zhong Hua Quan
, De Shuang Huang
, Kun Hong Liu
, Kwok Wing Chau

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

7 Citations (Scopus)

Abstract

This paper presents a new approach based on HMM/ANN hybrid for online signature verification. A group of ANNs are used as local probability estimators for an HMM. The Viterbi algorithm is employed to work out the global posterior probability of a model. The proposed HMM/ANN hybrid has a strong discriminant ability, i.e, from a local sense, the ANN can be regarded as an efficient classifier, and from a global sense, the posterior probability is consistent with that of a Bayes classifier. Finally, the experimental results show that this approach is promising and competing.

Original language	English
Title of host publication	The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings
Pages	402-405
Number of pages	4
DOIs	https://doi.org/10.1109/IJCNN.2007.4370990
Publication status	Published - 1 Dec 2007
Event	2007 International Joint Conference on Neural Networks, IJCNN 2007 - Orlando, FL, United States Duration: 12 Aug 2007 → 17 Aug 2007

Conference

Conference	2007 International Joint Conference on Neural Networks, IJCNN 2007
Country/Territory	United States
City	Orlando, FL
Period	12/08/07 → 17/08/07

Keywords

Artificial neural networks
Hidden Markov model
Online signature verification
Viterbi algorithm

ASJC Scopus subject areas

Software

More information

10.1109/IJCNN.2007.4370990

http://hdl.handle.net/10397/522

Cite this

@inproceedings{a49ecdab6ac14dd69a484c47d64c183c,

title = "A hybrid HMM/ANN based approach for online signature verification",

abstract = "This paper presents a new approach based on HMM/ANN hybrid for online signature verification. A group of ANNs are used as local probability estimators for an HMM. The Viterbi algorithm is employed to work out the global posterior probability of a model. The proposed HMM/ANN hybrid has a strong discriminant ability, i.e, from a local sense, the ANN can be regarded as an efficient classifier, and from a global sense, the posterior probability is consistent with that of a Bayes classifier. Finally, the experimental results show that this approach is promising and competing.",

keywords = "Artificial neural networks, Hidden Markov model, Online signature verification, Viterbi algorithm",

author = "Quan, \{Zhong Hua\} and Huang, \{De Shuang\} and Liu, \{Kun Hong\} and Chau, \{Kwok Wing\}",

year = "2007",

month = dec,

day = "1",

doi = "10.1109/IJCNN.2007.4370990",

language = "English",

isbn = "142441380X",

pages = "402--405",

booktitle = "The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings",

note = "2007 International Joint Conference on Neural Networks, IJCNN 2007 ; Conference date: 12-08-2007 Through 17-08-2007",

}

Quan, ZH, Huang, DS, Liu, KH & Chau, KW 2007, A hybrid HMM/ANN based approach for online signature verification. in The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings., 4370990, pp. 402-405, 2007 International Joint Conference on Neural Networks, IJCNN 2007, Orlando, FL, United States, 12/08/07. https://doi.org/10.1109/IJCNN.2007.4370990

A hybrid HMM/ANN based approach for online signature verification. / Quan, Zhong Hua; Huang, De Shuang; Liu, Kun Hong et al.
The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings. 2007. p. 402-405 4370990.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - A hybrid HMM/ANN based approach for online signature verification

AU - Quan, Zhong Hua

AU - Huang, De Shuang

AU - Liu, Kun Hong

AU - Chau, Kwok Wing

PY - 2007/12/1

Y1 - 2007/12/1

N2 - This paper presents a new approach based on HMM/ANN hybrid for online signature verification. A group of ANNs are used as local probability estimators for an HMM. The Viterbi algorithm is employed to work out the global posterior probability of a model. The proposed HMM/ANN hybrid has a strong discriminant ability, i.e, from a local sense, the ANN can be regarded as an efficient classifier, and from a global sense, the posterior probability is consistent with that of a Bayes classifier. Finally, the experimental results show that this approach is promising and competing.

AB - This paper presents a new approach based on HMM/ANN hybrid for online signature verification. A group of ANNs are used as local probability estimators for an HMM. The Viterbi algorithm is employed to work out the global posterior probability of a model. The proposed HMM/ANN hybrid has a strong discriminant ability, i.e, from a local sense, the ANN can be regarded as an efficient classifier, and from a global sense, the posterior probability is consistent with that of a Bayes classifier. Finally, the experimental results show that this approach is promising and competing.

KW - Artificial neural networks

KW - Hidden Markov model

KW - Online signature verification

KW - Viterbi algorithm

UR - https://www.scopus.com/pages/publications/51749115307

U2 - 10.1109/IJCNN.2007.4370990

DO - 10.1109/IJCNN.2007.4370990

M3 - Conference article published in proceeding or book

SN - 142441380X

SN - 9781424413805

SP - 402

EP - 405

BT - The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings

T2 - 2007 International Joint Conference on Neural Networks, IJCNN 2007

Y2 - 12 August 2007 through 17 August 2007

ER -

A hybrid HMM/ANN based approach for online signature verification

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this