Feature facial image recognition using VQ histogram in the DCT domain

Qiu Chen; Koji Kotani; Feifei Lee; Tadahiro Ohmi

doi:10.1117/12.855647

Feature facial image recognition using VQ histogram in the DCT domain

Qiu Chen, Koji Kotani, Feifei Lee, Tadahiro Ohmi

ENG - Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

In this paper, a novel algorithm using vector quantization (VQ) method for facial image recognition in DCT domain is presented. Firstly, feature vectors of facial image are generated by using DCT (Discrete Cosine transform) coefficients in low frequency domains. Then codevector referred count histogram, which is utilized as a very effective personal feature value, is obtained by Vector Quantization (VQ) processing. Publicly available AT&T database of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions, is used to evaluate the performance of the proposed algorithm. Experimental results show face recognition using proposed feature vector is very efficient. The highest average recognition rate of 94.8% is obtained.

Original language	English
Title of host publication	2nd International Conference on Digital Image Processing
DOIs	https://doi.org/10.1117/12.855647
Publication status	Published - 2010 Mar 22
Event	2nd International Conference on Digital Image Processing - Singapore, Singapore Duration: 2010 Feb 26 → 2010 Feb 28

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	7546
ISSN (Print)	0277-786X

Other

Other	2nd International Conference on Digital Image Processing
Country	Singapore
City	Singapore
Period	10/2/26 → 10/2/28

Keywords

DCT domain
Face recognition
Vector quantization (VQ)

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.855647

Fingerprint Dive into the research topics of 'Feature facial image recognition using VQ histogram in the DCT domain'. Together they form a unique fingerprint.

Cite this

Chen, Q., Kotani, K., Lee, F., & Ohmi, T. (2010). Feature facial image recognition using VQ histogram in the DCT domain. In 2nd International Conference on Digital Image Processing [75460J] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7546). https://doi.org/10.1117/12.855647

Feature facial image recognition using VQ histogram in the DCT domain. / Chen, Qiu; Kotani, Koji; Lee, Feifei; Ohmi, Tadahiro.

2nd International Conference on Digital Image Processing. 2010. 75460J (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7546).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Chen, Q, Kotani, K, Lee, F & Ohmi, T 2010, Feature facial image recognition using VQ histogram in the DCT domain. in 2nd International Conference on Digital Image Processing., 75460J, Proceedings of SPIE - The International Society for Optical Engineering, vol. 7546, 2nd International Conference on Digital Image Processing, Singapore, Singapore, 10/2/26. https://doi.org/10.1117/12.855647

@inproceedings{fca798d1d90c43449c9b2317afcaf1a8,

title = "Feature facial image recognition using VQ histogram in the DCT domain",

abstract = "In this paper, a novel algorithm using vector quantization (VQ) method for facial image recognition in DCT domain is presented. Firstly, feature vectors of facial image are generated by using DCT (Discrete Cosine transform) coefficients in low frequency domains. Then codevector referred count histogram, which is utilized as a very effective personal feature value, is obtained by Vector Quantization (VQ) processing. Publicly available AT&T database of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions, is used to evaluate the performance of the proposed algorithm. Experimental results show face recognition using proposed feature vector is very efficient. The highest average recognition rate of 94.8% is obtained.",

keywords = "DCT domain, Face recognition, Vector quantization (VQ)",

author = "Qiu Chen and Koji Kotani and Feifei Lee and Tadahiro Ohmi",

year = "2010",

month = mar,

day = "22",

doi = "10.1117/12.855647",

language = "English",

isbn = "9780819479426",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

booktitle = "2nd International Conference on Digital Image Processing",

note = "2nd International Conference on Digital Image Processing ; Conference date: 26-02-2010 Through 28-02-2010",

}

TY - GEN

T1 - Feature facial image recognition using VQ histogram in the DCT domain

AU - Chen, Qiu

AU - Kotani, Koji

AU - Lee, Feifei

AU - Ohmi, Tadahiro

PY - 2010/3/22

Y1 - 2010/3/22

N2 - In this paper, a novel algorithm using vector quantization (VQ) method for facial image recognition in DCT domain is presented. Firstly, feature vectors of facial image are generated by using DCT (Discrete Cosine transform) coefficients in low frequency domains. Then codevector referred count histogram, which is utilized as a very effective personal feature value, is obtained by Vector Quantization (VQ) processing. Publicly available AT&T database of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions, is used to evaluate the performance of the proposed algorithm. Experimental results show face recognition using proposed feature vector is very efficient. The highest average recognition rate of 94.8% is obtained.

AB - In this paper, a novel algorithm using vector quantization (VQ) method for facial image recognition in DCT domain is presented. Firstly, feature vectors of facial image are generated by using DCT (Discrete Cosine transform) coefficients in low frequency domains. Then codevector referred count histogram, which is utilized as a very effective personal feature value, is obtained by Vector Quantization (VQ) processing. Publicly available AT&T database of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions, is used to evaluate the performance of the proposed algorithm. Experimental results show face recognition using proposed feature vector is very efficient. The highest average recognition rate of 94.8% is obtained.

KW - DCT domain

KW - Face recognition

KW - Vector quantization (VQ)

UR - http://www.scopus.com/inward/record.url?scp=77949429023&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949429023&partnerID=8YFLogxK

U2 - 10.1117/12.855647

DO - 10.1117/12.855647

M3 - Conference contribution

AN - SCOPUS:77949429023

SN - 9780819479426

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - 2nd International Conference on Digital Image Processing

T2 - 2nd International Conference on Digital Image Processing

Y2 - 26 February 2010 through 28 February 2010

ER -