Enhanced discriminant linear regression classification for face recognition

Xiaochao Qu; Hyong Joong Kim

doi:10.1109/ISSNIP.2014.6827696

Enhanced discriminant linear regression classification for face recognition

Xiaochao Qu, Hyong Joong Kim

Graduate School of Information Security

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

3 Citations (Scopus)

Abstract

Linear Discriminant regression classification (L-DRC) embeds the fisher criterion into the linear regression classification (LRC) and can achieve more robust classification performance for face recognition. In this paper, we propose an enhanced discriminant linear regression classification (EDLRC) algorithm to further improve the discriminant power of LDRC. When calculating the between-class reconstruction error (BCRE), only those classes that are more easily to be misclassified into are considered. After maximizing the ratio of BCRE and within-class reconstruction error (WCRE), the obtained projection matrix in EDLRC is more effective than the projection matrix in LDRC, which is verified by extensive experiments.

Original language	English
Title of host publication	IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings
Publisher	IEEE Computer Society
ISBN (Print)	9781479928439
DOIs	https://doi.org/10.1109/ISSNIP.2014.6827696
Publication status	Published - 2014 Jan 1
Event	9th IEEE International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE ISSNIP 2014 - Singapore, Singapore Duration: 2014 Apr 21 → 2014 Apr 24

Other

Other	9th IEEE International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE ISSNIP 2014
Country	Singapore
City	Singapore
Period	14/4/21 → 14/4/24

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Information Systems

Access to Document

10.1109/ISSNIP.2014.6827696

Fingerprint Dive into the research topics of 'Enhanced discriminant linear regression classification for face recognition'. Together they form a unique fingerprint.

Cite this

Qu, X., & Kim, H. J. (2014). Enhanced discriminant linear regression classification for face recognition. In IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings [6827696] IEEE Computer Society. https://doi.org/10.1109/ISSNIP.2014.6827696

Enhanced discriminant linear regression classification for face recognition. / Qu, Xiaochao; Kim, Hyong Joong.

IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings. IEEE Computer Society, 2014. 6827696.

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

Qu, X & Kim, HJ 2014, Enhanced discriminant linear regression classification for face recognition. in IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings., 6827696, IEEE Computer Society, 9th IEEE International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE ISSNIP 2014, Singapore, Singapore, 14/4/21. https://doi.org/10.1109/ISSNIP.2014.6827696

@inproceedings{649951dbb3654e5ea8b8bbf4d566439c,

title = "Enhanced discriminant linear regression classification for face recognition",

abstract = "Linear Discriminant regression classification (L-DRC) embeds the fisher criterion into the linear regression classification (LRC) and can achieve more robust classification performance for face recognition. In this paper, we propose an enhanced discriminant linear regression classification (EDLRC) algorithm to further improve the discriminant power of LDRC. When calculating the between-class reconstruction error (BCRE), only those classes that are more easily to be misclassified into are considered. After maximizing the ratio of BCRE and within-class reconstruction error (WCRE), the obtained projection matrix in EDLRC is more effective than the projection matrix in LDRC, which is verified by extensive experiments.",

author = "Xiaochao Qu and Kim, {Hyong Joong}",

year = "2014",

month = jan,

day = "1",

doi = "10.1109/ISSNIP.2014.6827696",

language = "English",

isbn = "9781479928439",

booktitle = "IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings",

publisher = "IEEE Computer Society",

note = "9th IEEE International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE ISSNIP 2014 ; Conference date: 21-04-2014 Through 24-04-2014",

}

TY - GEN

T1 - Enhanced discriminant linear regression classification for face recognition

AU - Qu, Xiaochao

AU - Kim, Hyong Joong

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Linear Discriminant regression classification (L-DRC) embeds the fisher criterion into the linear regression classification (LRC) and can achieve more robust classification performance for face recognition. In this paper, we propose an enhanced discriminant linear regression classification (EDLRC) algorithm to further improve the discriminant power of LDRC. When calculating the between-class reconstruction error (BCRE), only those classes that are more easily to be misclassified into are considered. After maximizing the ratio of BCRE and within-class reconstruction error (WCRE), the obtained projection matrix in EDLRC is more effective than the projection matrix in LDRC, which is verified by extensive experiments.

AB - Linear Discriminant regression classification (L-DRC) embeds the fisher criterion into the linear regression classification (LRC) and can achieve more robust classification performance for face recognition. In this paper, we propose an enhanced discriminant linear regression classification (EDLRC) algorithm to further improve the discriminant power of LDRC. When calculating the between-class reconstruction error (BCRE), only those classes that are more easily to be misclassified into are considered. After maximizing the ratio of BCRE and within-class reconstruction error (WCRE), the obtained projection matrix in EDLRC is more effective than the projection matrix in LDRC, which is verified by extensive experiments.

UR - http://www.scopus.com/inward/record.url?scp=84903727721&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903727721&partnerID=8YFLogxK

U2 - 10.1109/ISSNIP.2014.6827696

DO - 10.1109/ISSNIP.2014.6827696

M3 - Conference contribution

AN - SCOPUS:84903727721

SN - 9781479928439

BT - IEEE ISSNIP 2014 - 2014 IEEE 9th International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Conference Proceedings

PB - IEEE Computer Society

T2 - 9th IEEE International Conference on Intelligent Sensors, Sensor Networks and Information Processing, IEEE ISSNIP 2014

Y2 - 21 April 2014 through 24 April 2014

ER -