DWT based HMM for face recognition

Linlin Shen; Zhen Ji; Li Bai; Chen Xu

doi:10.1007/s11767-007-0028-x

DWT based HMM for face recognition

Linlin Shen
, Zhen Ji
, Li Bai
, Chen Xu

Research output: Journal Publication › Article › peer-review

15 Citations (Scopus)

Abstract

A novel Discrete Wavelet Transform (DWT) based Hidden Markov Module (HMM) for face recognition is presented in this letter. To improve the accuracy of HMM based face recognition algorithm, DWT is used to replace Discrete Cosine Transform (DCT) for observation sequence extraction. Extensive experiments are conducted on two public databases and the results show that the proposed method can improve the accuracy significantly, especially when the face database is large and only few training images are available.

Original language	English
Pages (from-to)	835-837
Number of pages	3
Journal	Journal of Electronics
Volume	24
Issue number	6
DOIs	https://doi.org/10.1007/s11767-007-0028-x
Publication status	Published - Nov 2007
Externally published	Yes

Free Keywords

Discrete Wavelet Transform (DWT)
Face recognition
Hidden Markov Model (HMM)

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1007/s11767-007-0028-x

Cite this

@article{16b045eed62f45d2b9c0827d8d343f01,

title = "DWT based HMM for face recognition",

abstract = "A novel Discrete Wavelet Transform (DWT) based Hidden Markov Module (HMM) for face recognition is presented in this letter. To improve the accuracy of HMM based face recognition algorithm, DWT is used to replace Discrete Cosine Transform (DCT) for observation sequence extraction. Extensive experiments are conducted on two public databases and the results show that the proposed method can improve the accuracy significantly, especially when the face database is large and only few training images are available.",

keywords = "Discrete Wavelet Transform (DWT), Face recognition, Hidden Markov Model (HMM)",

author = "Linlin Shen and Zhen Ji and Li Bai and Chen Xu",

note = "Funding Information: 1 Manuscript received date: February 1, 2007; revised date: April 3, 2007. Supported by SZU R/D Fund 200746, the National Natural Science Foundation of China (No. 60572100), Royal Society (U.K.) International Joint Projects 2006/R3-Cost Share with NSFC, Foundation of State Key Laboratory of Networking and Switching Technol-ogy (Beijing University of Posts and Telecommunications, China) and Guangdong Natural Science Foundation (No.06105776). Communication author: Shen Linlin, born in 1976, male, Ph.D., assistant professor. Faculty of Information Engi-neering, Shenzhen University, Shenzhen 518060, China. Email: llshen@szu.edu.cn.",

year = "2007",

month = nov,

doi = "10.1007/s11767-007-0028-x",

language = "English",

volume = "24",

pages = "835--837",

journal = "Journal of Electronics",

issn = "0217-9822",

publisher = "Science Press",

number = "6",

}

TY - JOUR

T1 - DWT based HMM for face recognition

AU - Shen, Linlin

AU - Ji, Zhen

AU - Bai, Li

AU - Xu, Chen

N1 - Funding Information: 1 Manuscript received date: February 1, 2007; revised date: April 3, 2007. Supported by SZU R/D Fund 200746, the National Natural Science Foundation of China (No. 60572100), Royal Society (U.K.) International Joint Projects 2006/R3-Cost Share with NSFC, Foundation of State Key Laboratory of Networking and Switching Technol-ogy (Beijing University of Posts and Telecommunications, China) and Guangdong Natural Science Foundation (No.06105776). Communication author: Shen Linlin, born in 1976, male, Ph.D., assistant professor. Faculty of Information Engi-neering, Shenzhen University, Shenzhen 518060, China. Email: llshen@szu.edu.cn.

PY - 2007/11

Y1 - 2007/11

N2 - A novel Discrete Wavelet Transform (DWT) based Hidden Markov Module (HMM) for face recognition is presented in this letter. To improve the accuracy of HMM based face recognition algorithm, DWT is used to replace Discrete Cosine Transform (DCT) for observation sequence extraction. Extensive experiments are conducted on two public databases and the results show that the proposed method can improve the accuracy significantly, especially when the face database is large and only few training images are available.

AB - A novel Discrete Wavelet Transform (DWT) based Hidden Markov Module (HMM) for face recognition is presented in this letter. To improve the accuracy of HMM based face recognition algorithm, DWT is used to replace Discrete Cosine Transform (DCT) for observation sequence extraction. Extensive experiments are conducted on two public databases and the results show that the proposed method can improve the accuracy significantly, especially when the face database is large and only few training images are available.

KW - Discrete Wavelet Transform (DWT)

KW - Face recognition

KW - Hidden Markov Model (HMM)

UR - https://www.scopus.com/pages/publications/36849022615

U2 - 10.1007/s11767-007-0028-x

DO - 10.1007/s11767-007-0028-x

M3 - Article

AN - SCOPUS:36849022615

SN - 0217-9822

VL - 24

SP - 835

EP - 837

JO - Journal of Electronics

JF - Journal of Electronics

IS - 6

ER -

DWT based HMM for face recognition

Abstract

Free Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this