Two-dimensional discriminant transform for face recognition

Jian Yang; David Zhang; Xu Yong; Jing Yu Yang

doi:10.1016/j.patcog.2004.11.019

Two-dimensional discriminant transform for face recognition

Jian Yang^*
, David Zhang
, Xu Yong
, Jing Yu Yang

^*Corresponding author for this work

Hong Kong Polytechnic University
Nanjing University of Science and Technology

Research output: Contribution to journal › Article › peer-review

293 Scopus citations

Abstract

This paper develops a new image feature extraction and recognition method coined two-dimensional linear discriminant analysis (2DLDA). 2DLDA provides a sequentially optimal image compression mechanism, making the discriminant information compact into the up-left corner of the image. Also, 2DLDA suggests a feature selection strategy to select the most discriminative features from the corner. 2DLDA is tested and evaluated using the AT&T face database. The experimental results show 2DLDA is more effective and computationally more efficient than the current LDA algorithms for face feature extraction and recognition.

Original language	English
Pages (from-to)	1125-1129
Number of pages	5
Journal	Pattern Recognition
Volume	38
Issue number	7
DOIs	https://doi.org/10.1016/j.patcog.2004.11.019
State	Published - Jul 2005
Externally published	Yes

Keywords

Face recognition
Feature extraction
Fisher linear discriminant analysis (fld or lda)
Fisherfaces
Two-dimensional data analysis

Access to Document

10.1016/j.patcog.2004.11.019

Cite this

@article{2bac240adc14421db08aa3125cd739af,

title = "Two-dimensional discriminant transform for face recognition",

abstract = "This paper develops a new image feature extraction and recognition method coined two-dimensional linear discriminant analysis (2DLDA). 2DLDA provides a sequentially optimal image compression mechanism, making the discriminant information compact into the up-left corner of the image. Also, 2DLDA suggests a feature selection strategy to select the most discriminative features from the corner. 2DLDA is tested and evaluated using the AT\&T face database. The experimental results show 2DLDA is more effective and computationally more efficient than the current LDA algorithms for face feature extraction and recognition.",

keywords = "Face recognition, Feature extraction, Fisher linear discriminant analysis (fld or lda), Fisherfaces, Two-dimensional data analysis",

author = "Jian Yang and David Zhang and Xu Yong and Yang, \{Jing Yu\}",

year = "2005",

month = jul,

doi = "10.1016/j.patcog.2004.11.019",

language = "英语",

volume = "38",

pages = "1125--1129",

journal = "Pattern Recognition",

issn = "0031-3203",

publisher = "Elsevier Ltd",

number = "7",

}

TY - JOUR

T1 - Two-dimensional discriminant transform for face recognition

AU - Yang, Jian

AU - Zhang, David

AU - Yong, Xu

AU - Yang, Jing Yu

PY - 2005/7

Y1 - 2005/7

N2 - This paper develops a new image feature extraction and recognition method coined two-dimensional linear discriminant analysis (2DLDA). 2DLDA provides a sequentially optimal image compression mechanism, making the discriminant information compact into the up-left corner of the image. Also, 2DLDA suggests a feature selection strategy to select the most discriminative features from the corner. 2DLDA is tested and evaluated using the AT&T face database. The experimental results show 2DLDA is more effective and computationally more efficient than the current LDA algorithms for face feature extraction and recognition.

AB - This paper develops a new image feature extraction and recognition method coined two-dimensional linear discriminant analysis (2DLDA). 2DLDA provides a sequentially optimal image compression mechanism, making the discriminant information compact into the up-left corner of the image. Also, 2DLDA suggests a feature selection strategy to select the most discriminative features from the corner. 2DLDA is tested and evaluated using the AT&T face database. The experimental results show 2DLDA is more effective and computationally more efficient than the current LDA algorithms for face feature extraction and recognition.

KW - Face recognition

KW - Feature extraction

KW - Fisher linear discriminant analysis (fld or lda)

KW - Fisherfaces

KW - Two-dimensional data analysis

UR - https://www.scopus.com/pages/publications/17444363017

U2 - 10.1016/j.patcog.2004.11.019

DO - 10.1016/j.patcog.2004.11.019

M3 - 文章

AN - SCOPUS:17444363017

SN - 0031-3203

VL - 38

SP - 1125

EP - 1129

JO - Pattern Recognition

JF - Pattern Recognition

IS - 7

ER -

Two-dimensional discriminant transform for face recognition

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this