Proceedings of the 2013 International Conference on Advanced ICT and Education

Spectral Regression based Local Discriminant Embedding Algorithm for Face Recognition

Authors
Bei Huang
Corresponding Author
Bei Huang
Available Online August 2013.
DOI
10.2991/icaicte.2013.120How to use a DOI?
Keywords
Face Recognition, Local Discriminant Embedding, Spectral Regression
Abstract

Local discriminant embedding algorithm (LDE) can get better recognition performance than the conventional dimensionality reduction algorithms based on subspaces techniques, but LDE is weak generalization performance for high dimension small sample and has huge workload to decompose dense matrix. In this paper, the SR-LDE algorithm is proposed. The spectral regression method is introduced into LDE to improve its generalization performance and reduce complexity for dense matrix decomposition. The experiments show that SR-LDE algorithm has better performance on recognition rate and computing speed.

Copyright
© 2013, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2013 International Conference on Advanced ICT and Education
Series
Advances in Intelligent Systems Research
Publication Date
August 2013
ISBN
10.2991/icaicte.2013.120
ISSN
1951-6851
DOI
10.2991/icaicte.2013.120How to use a DOI?
Copyright
© 2013, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Bei Huang
PY  - 2013/08
DA  - 2013/08
TI  - Spectral Regression based Local Discriminant Embedding Algorithm for Face Recognition
BT  - Proceedings of the 2013 International Conference on Advanced ICT and Education
PB  - Atlantis Press
SP  - 587
EP  - 591
SN  - 1951-6851
UR  - https://doi.org/10.2991/icaicte.2013.120
DO  - 10.2991/icaicte.2013.120
ID  - Huang2013/08
ER  -