Face recognition based on nonlinear DCT discriminant feature extraction using improved kernel DCV

Sheng Li; Yong Fang Yao; Xiao Yuan Jing; Heng Chang; Shi Qiang Gao; Dapeng Zhang; Jing Yu Yang

doi:10.1587/transinf.E92.D.2527

Face recognition based on nonlinear DCT discriminant feature extraction using improved kernel DCV

Sheng Li, Yong Fang Yao, Xiao Yuan Jing, Heng Chang, Shi Qiang Gao, Dapeng Zhang, Jing Yu Yang

Research output: Journal article publication › Journal article › Academic research › peer-review

9 Citations (Scopus)

Abstract

This letter proposes a nonlinear DCT discriminant feature extraction approach for face recognition. The proposed approach first selects appropriate DCT frequency bands according to their levels of nonlinear discrimination. Then, this approach extracts nonlinear discriminant features from the selected DCT bands by presenting a new kernel discriminant method, i.e. the improved kernel discriminative common vector (KDCV) method. Experiments on the public FERET database show that this new approach is more effective than several related methods.

Original language	English
Pages (from-to)	2527-2530
Number of pages	4
Journal	IEICE Transactions on Information and Systems
Volume	E92-D
Issue number	12
DOIs	https://doi.org/10.1587/transinf.E92.D.2527
Publication status	Published - 1 Jan 2009

Keywords

DCT frequency bands selection
Face recognition
Nonlinear DCT feature extraction
The improved KDCV

ASJC Scopus subject areas

Software
Hardware and Architecture
Computer Vision and Pattern Recognition
Electrical and Electronic Engineering
Artificial Intelligence

More information

10.1587/transinf.E92.D.2527

Cite this

@article{ee6cbb37b50d45748b3a1979385bef95,

title = "Face recognition based on nonlinear DCT discriminant feature extraction using improved kernel DCV",

abstract = "This letter proposes a nonlinear DCT discriminant feature extraction approach for face recognition. The proposed approach first selects appropriate DCT frequency bands according to their levels of nonlinear discrimination. Then, this approach extracts nonlinear discriminant features from the selected DCT bands by presenting a new kernel discriminant method, i.e. the improved kernel discriminative common vector (KDCV) method. Experiments on the public FERET database show that this new approach is more effective than several related methods.",

keywords = "DCT frequency bands selection, Face recognition, Nonlinear DCT feature extraction, The improved KDCV",

author = "Sheng Li and Yao, {Yong Fang} and Jing, {Xiao Yuan} and Heng Chang and Gao, {Shi Qiang} and Dapeng Zhang and Yang, {Jing Yu}",

year = "2009",

month = jan,

day = "1",

doi = "10.1587/transinf.E92.D.2527",

language = "English",

volume = "E92-D",

pages = "2527--2530",

journal = "IEICE Transactions on Information and Systems",

issn = "0916-8532",

publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",

number = "12",

}

TY - JOUR

T1 - Face recognition based on nonlinear DCT discriminant feature extraction using improved kernel DCV

AU - Li, Sheng

AU - Yao, Yong Fang

AU - Jing, Xiao Yuan

AU - Chang, Heng

AU - Gao, Shi Qiang

AU - Zhang, Dapeng

AU - Yang, Jing Yu

PY - 2009/1/1

Y1 - 2009/1/1

N2 - This letter proposes a nonlinear DCT discriminant feature extraction approach for face recognition. The proposed approach first selects appropriate DCT frequency bands according to their levels of nonlinear discrimination. Then, this approach extracts nonlinear discriminant features from the selected DCT bands by presenting a new kernel discriminant method, i.e. the improved kernel discriminative common vector (KDCV) method. Experiments on the public FERET database show that this new approach is more effective than several related methods.

AB - This letter proposes a nonlinear DCT discriminant feature extraction approach for face recognition. The proposed approach first selects appropriate DCT frequency bands according to their levels of nonlinear discrimination. Then, this approach extracts nonlinear discriminant features from the selected DCT bands by presenting a new kernel discriminant method, i.e. the improved kernel discriminative common vector (KDCV) method. Experiments on the public FERET database show that this new approach is more effective than several related methods.

KW - DCT frequency bands selection

KW - Face recognition

KW - Nonlinear DCT feature extraction

KW - The improved KDCV

UR - http://www.scopus.com/inward/record.url?scp=77950272306&partnerID=8YFLogxK

U2 - 10.1587/transinf.E92.D.2527

DO - 10.1587/transinf.E92.D.2527

M3 - Journal article

SN - 0916-8532

VL - E92-D

SP - 2527

EP - 2530

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

IS - 12

ER -

Face recognition based on nonlinear DCT discriminant feature extraction using improved kernel DCV

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this