2D(PC) 2 a for face recognition with one training image per person

Jun Bao Li; Shu Chuan Chu; Jeng Shyang Pan

doi:10.1109/IIH-MSP.2007.3

2D(PC) ² a for face recognition with one training image per person

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

^*Corresponding author for this work

Faculty of Computing

Cheng Shiu University
National Kaohsiung University of Science and Technology

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

2 Scopus citations

Abstract

In the real-world application of face recognition system, owing to the difficulties of collecting samples or storage space of systems, only one sample image per person is stored in the system, which is so-called one sample per person problem. In this paper, we propose a novel algorithm, called 2D(PC) ² A, to solve this problem. The procedure of 2D(PC) ² A can be divided into the three stages: 1) creating the combined image from the original image 2) performing 2DPCA on the combined images; 3) classifying a new face based on assembled matrix distance (AMD). Experiments implemented on two real dataseis show that 2D(PC)2A method is an efficient and practical approach for face recognition.

Original language	English
Title of host publication	Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.
Pages	131-134
Number of pages	4
DOIs	https://doi.org/10.1109/IIH-MSP.2007.3
State	Published - 2007
Event	3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007 - Kaohsiung, Taiwan, Province of China Duration: 26 Nov 2007 → 28 Nov 2007

Publication series

Name	Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.
Volume	1

Conference

Conference	3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007
Country/Territory	Taiwan, Province of China
City	Kaohsiung
Period	26/11/07 → 28/11/07

Access to Document

10.1109/IIH-MSP.2007.3

Cite this

Li, J. B., Chu, S. C., & Pan, J. S. (2007). 2D(PC) ² a for face recognition with one training image per person. In Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007. (pp. 131-134). Article 4457509 (Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.; Vol. 1). https://doi.org/10.1109/IIH-MSP.2007.3

Li, Jun Bao ; Chu, Shu Chuan ; Pan, Jeng Shyang. / 2D(PC) ² a for face recognition with one training image per person. Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.. 2007. pp. 131-134 (Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.).

@inproceedings{d20405fa995242a8b30015c5602cb952,

title = "2D(PC) 2 a for face recognition with one training image per person",

abstract = "In the real-world application of face recognition system, owing to the difficulties of collecting samples or storage space of systems, only one sample image per person is stored in the system, which is so-called one sample per person problem. In this paper, we propose a novel algorithm, called 2D(PC) 2 A, to solve this problem. The procedure of 2D(PC) 2 A can be divided into the three stages: 1) creating the combined image from the original image 2) performing 2DPCA on the combined images; 3) classifying a new face based on assembled matrix distance (AMD). Experiments implemented on two real dataseis show that 2D(PC)2A method is an efficient and practical approach for face recognition.",

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

year = "2007",

doi = "10.1109/IIH-MSP.2007.3",

language = "英语",

isbn = "0769529941",

series = "Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.",

pages = "131--134",

booktitle = "Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.",

note = "3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007 ; Conference date: 26-11-2007 Through 28-11-2007",

}

Li, JB, Chu, SC & Pan, JS 2007, 2D(PC) ² a for face recognition with one training image per person. in Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.., 4457509, Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007., vol. 1, pp. 131-134, 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007, Kaohsiung, Taiwan, Province of China, 26/11/07. https://doi.org/10.1109/IIH-MSP.2007.3

2D(PC) ² a for face recognition with one training image per person. / Li, Jun Bao; Chu, Shu Chuan; Pan, Jeng Shyang.
Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.. 2007. p. 131-134 4457509 (Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.; Vol. 1).

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

TY - GEN

T1 - 2D(PC) 2 a for face recognition with one training image per person

AU - Li, Jun Bao

AU - Chu, Shu Chuan

AU - Pan, Jeng Shyang

PY - 2007

Y1 - 2007

N2 - In the real-world application of face recognition system, owing to the difficulties of collecting samples or storage space of systems, only one sample image per person is stored in the system, which is so-called one sample per person problem. In this paper, we propose a novel algorithm, called 2D(PC) 2 A, to solve this problem. The procedure of 2D(PC) 2 A can be divided into the three stages: 1) creating the combined image from the original image 2) performing 2DPCA on the combined images; 3) classifying a new face based on assembled matrix distance (AMD). Experiments implemented on two real dataseis show that 2D(PC)2A method is an efficient and practical approach for face recognition.

AB - In the real-world application of face recognition system, owing to the difficulties of collecting samples or storage space of systems, only one sample image per person is stored in the system, which is so-called one sample per person problem. In this paper, we propose a novel algorithm, called 2D(PC) 2 A, to solve this problem. The procedure of 2D(PC) 2 A can be divided into the three stages: 1) creating the combined image from the original image 2) performing 2DPCA on the combined images; 3) classifying a new face based on assembled matrix distance (AMD). Experiments implemented on two real dataseis show that 2D(PC)2A method is an efficient and practical approach for face recognition.

UR - https://www.scopus.com/pages/publications/47349118101

U2 - 10.1109/IIH-MSP.2007.3

DO - 10.1109/IIH-MSP.2007.3

M3 - 会议稿件

AN - SCOPUS:47349118101

SN - 0769529941

SN - 9780769529943

T3 - Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.

SP - 131

EP - 134

BT - Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.

T2 - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007

Y2 - 26 November 2007 through 28 November 2007

ER -

Li JB, Chu SC, Pan JS. 2D(PC) ² a for face recognition with one training image per person. In Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.. 2007. p. 131-134. 4457509. (Proceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.). doi: 10.1109/IIH-MSP.2007.3