Fusing 2DKPCA and 2D(PC)2a for image matrix based face recognition with one training sample per person

Jun Bao Li; Shu An Chu; Jeng Shyang Pan

doi:10.1109/ICICIC.2008.284

Fusing 2DKPCA and 2D(PC)²a for image matrix based face recognition with one training sample per person

Jun Bao Li^*
, Shu An Chu
, Jeng Shyang Pan

^*Corresponding author for this work

Faculty of Computing

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

Abstract

In the face recognition area, a so-called one sample per person problem occurred owing to the difficulties of collecting samples or storage space of systems. In this paper, we present a unified framework for image matrix based face recognition with one training sample per person. Firstly, the nonlinear and linear facial features are using proposed 2DKPCA and 2D(PC)²A method, the face images are directly used for feature extraction, and secondly a parallel fusion method is applied to fuse the facial features to construct the combined features. Experiments are implemented on three face databases to demonstrate the feasibility of proposed algorithm.

Original language	English
Title of host publication	3rd International Conference on Innovative Computing Information and Control, ICICIC'08
DOIs	https://doi.org/10.1109/ICICIC.2008.284
State	Published - 2008
Event	3rd International Conference on Innovative Computing Information and Control, ICICIC'08 - Dalian, Liaoning, China Duration: 18 Jun 2008 → 20 Jun 2008

Publication series

Name	3rd International Conference on Innovative Computing Information and Control, ICICIC'08

Conference

Conference	3rd International Conference on Innovative Computing Information and Control, ICICIC'08
Country/Territory	China
City	Dalian, Liaoning
Period	18/06/08 → 20/06/08

Keywords

Face recognition
Kernel method
One sample per person problem
PCA

Access to Document

10.1109/ICICIC.2008.284

Cite this

Li, J. B., Chu, S. A., & Pan, J. S. (2008). Fusing 2DKPCA and 2D(PC)²a for image matrix based face recognition with one training sample per person. In 3rd International Conference on Innovative Computing Information and Control, ICICIC'08 Article 4603728 (3rd International Conference on Innovative Computing Information and Control, ICICIC'08). https://doi.org/10.1109/ICICIC.2008.284

@inproceedings{02dd3c19b5ed45fc82ce6f499a76c321,

title = "Fusing 2DKPCA and 2D(PC)2a for image matrix based face recognition with one training sample per person",

abstract = "In the face recognition area, a so-called one sample per person problem occurred owing to the difficulties of collecting samples or storage space of systems. In this paper, we present a unified framework for image matrix based face recognition with one training sample per person. Firstly, the nonlinear and linear facial features are using proposed 2DKPCA and 2D(PC)2A method, the face images are directly used for feature extraction, and secondly a parallel fusion method is applied to fuse the facial features to construct the combined features. Experiments are implemented on three face databases to demonstrate the feasibility of proposed algorithm.",

keywords = "Face recognition, Kernel method, One sample per person problem, PCA",

author = "Li, \{Jun Bao\} and Chu, \{Shu An\} and Pan, \{Jeng Shyang\}",

year = "2008",

doi = "10.1109/ICICIC.2008.284",

language = "英语",

isbn = "9780769531618",

series = "3rd International Conference on Innovative Computing Information and Control, ICICIC'08",

booktitle = "3rd International Conference on Innovative Computing Information and Control, ICICIC'08",

note = "3rd International Conference on Innovative Computing Information and Control, ICICIC'08 ; Conference date: 18-06-2008 Through 20-06-2008",

}

Li, JB, Chu, SA & Pan, JS 2008, Fusing 2DKPCA and 2D(PC)²a for image matrix based face recognition with one training sample per person. in 3rd International Conference on Innovative Computing Information and Control, ICICIC'08., 4603728, 3rd International Conference on Innovative Computing Information and Control, ICICIC'08, 3rd International Conference on Innovative Computing Information and Control, ICICIC'08, Dalian, Liaoning, China, 18/06/08. https://doi.org/10.1109/ICICIC.2008.284

Fusing 2DKPCA and 2D(PC)²a for image matrix based face recognition with one training sample per person. / Li, Jun Bao; Chu, Shu An; Pan, Jeng Shyang.
3rd International Conference on Innovative Computing Information and Control, ICICIC'08. 2008. 4603728 (3rd International Conference on Innovative Computing Information and Control, ICICIC'08).

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

TY - GEN

T1 - Fusing 2DKPCA and 2D(PC)2a for image matrix based face recognition with one training sample per person

AU - Li, Jun Bao

AU - Chu, Shu An

AU - Pan, Jeng Shyang

PY - 2008

Y1 - 2008

N2 - In the face recognition area, a so-called one sample per person problem occurred owing to the difficulties of collecting samples or storage space of systems. In this paper, we present a unified framework for image matrix based face recognition with one training sample per person. Firstly, the nonlinear and linear facial features are using proposed 2DKPCA and 2D(PC)2A method, the face images are directly used for feature extraction, and secondly a parallel fusion method is applied to fuse the facial features to construct the combined features. Experiments are implemented on three face databases to demonstrate the feasibility of proposed algorithm.

AB - In the face recognition area, a so-called one sample per person problem occurred owing to the difficulties of collecting samples or storage space of systems. In this paper, we present a unified framework for image matrix based face recognition with one training sample per person. Firstly, the nonlinear and linear facial features are using proposed 2DKPCA and 2D(PC)2A method, the face images are directly used for feature extraction, and secondly a parallel fusion method is applied to fuse the facial features to construct the combined features. Experiments are implemented on three face databases to demonstrate the feasibility of proposed algorithm.

KW - Face recognition

KW - Kernel method

KW - One sample per person problem

KW - PCA

UR - https://www.scopus.com/pages/publications/52449084174

U2 - 10.1109/ICICIC.2008.284

DO - 10.1109/ICICIC.2008.284

M3 - 会议稿件

AN - SCOPUS:52449084174

SN - 9780769531618

T3 - 3rd International Conference on Innovative Computing Information and Control, ICICIC'08

BT - 3rd International Conference on Innovative Computing Information and Control, ICICIC'08

T2 - 3rd International Conference on Innovative Computing Information and Control, ICICIC'08

Y2 - 18 June 2008 through 20 June 2008

ER -