Robust face recognition using multiple self-organized Gabor features and local similarity matching

Saleh Aly, Atsushi Shimada, Naoyuki Tsuruta, Rin-Ichiro Taniguchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Gabor-based face representation has achieved enormous success in face recognition. However, one drawback of Gabor-based face representation is the huge amount of data that must be stored. Due to the nonlinear structure of the data obtained from Gabor response, classical linear projection methods like principal component analysis fail to learn the distribution of the data. A nonlinear projection method based on a set of self-organizing maps is employed to capture this nonlinearity and to represent face in a new reduced feature space. The Multiple Self-Organized Gabor Features (MSOGF) algorithm is used to represent the input image using all winner indices from each SOM map. A new local matching algorithm based on the similarity between local features is also proposed to classify unlabeled data. Experimental results on FERET database prove that the proposed method is robust to expression variations.

Original languageEnglish
Title of host publicationProceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010
Pages2909-2912
Number of pages4
DOIs
Publication statusPublished - 2010
Event2010 20th International Conference on Pattern Recognition, ICPR 2010 - Istanbul, Turkey
Duration: Aug 23 2010Aug 26 2010

Other

Other2010 20th International Conference on Pattern Recognition, ICPR 2010
CountryTurkey
CityIstanbul
Period8/23/108/26/10

Fingerprint

Face recognition
Self organizing maps
Principal component analysis

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Aly, S., Shimada, A., Tsuruta, N., & Taniguchi, R-I. (2010). Robust face recognition using multiple self-organized Gabor features and local similarity matching. In Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010 (pp. 2909-2912). [5597061] https://doi.org/10.1109/ICPR.2010.713

Robust face recognition using multiple self-organized Gabor features and local similarity matching. / Aly, Saleh; Shimada, Atsushi; Tsuruta, Naoyuki; Taniguchi, Rin-Ichiro.

Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010. 2010. p. 2909-2912 5597061.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Aly, S, Shimada, A, Tsuruta, N & Taniguchi, R-I 2010, Robust face recognition using multiple self-organized Gabor features and local similarity matching. in Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010., 5597061, pp. 2909-2912, 2010 20th International Conference on Pattern Recognition, ICPR 2010, Istanbul, Turkey, 8/23/10. https://doi.org/10.1109/ICPR.2010.713
Aly S, Shimada A, Tsuruta N, Taniguchi R-I. Robust face recognition using multiple self-organized Gabor features and local similarity matching. In Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010. 2010. p. 2909-2912. 5597061 https://doi.org/10.1109/ICPR.2010.713
Aly, Saleh ; Shimada, Atsushi ; Tsuruta, Naoyuki ; Taniguchi, Rin-Ichiro. / Robust face recognition using multiple self-organized Gabor features and local similarity matching. Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010. 2010. pp. 2909-2912
@inproceedings{467a97096f284fc3a622da8977db4ef7,
title = "Robust face recognition using multiple self-organized Gabor features and local similarity matching",
abstract = "Gabor-based face representation has achieved enormous success in face recognition. However, one drawback of Gabor-based face representation is the huge amount of data that must be stored. Due to the nonlinear structure of the data obtained from Gabor response, classical linear projection methods like principal component analysis fail to learn the distribution of the data. A nonlinear projection method based on a set of self-organizing maps is employed to capture this nonlinearity and to represent face in a new reduced feature space. The Multiple Self-Organized Gabor Features (MSOGF) algorithm is used to represent the input image using all winner indices from each SOM map. A new local matching algorithm based on the similarity between local features is also proposed to classify unlabeled data. Experimental results on FERET database prove that the proposed method is robust to expression variations.",
author = "Saleh Aly and Atsushi Shimada and Naoyuki Tsuruta and Rin-Ichiro Taniguchi",
year = "2010",
doi = "10.1109/ICPR.2010.713",
language = "English",
isbn = "9780769541099",
pages = "2909--2912",
booktitle = "Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010",

}

TY - GEN

T1 - Robust face recognition using multiple self-organized Gabor features and local similarity matching

AU - Aly, Saleh

AU - Shimada, Atsushi

AU - Tsuruta, Naoyuki

AU - Taniguchi, Rin-Ichiro

PY - 2010

Y1 - 2010

N2 - Gabor-based face representation has achieved enormous success in face recognition. However, one drawback of Gabor-based face representation is the huge amount of data that must be stored. Due to the nonlinear structure of the data obtained from Gabor response, classical linear projection methods like principal component analysis fail to learn the distribution of the data. A nonlinear projection method based on a set of self-organizing maps is employed to capture this nonlinearity and to represent face in a new reduced feature space. The Multiple Self-Organized Gabor Features (MSOGF) algorithm is used to represent the input image using all winner indices from each SOM map. A new local matching algorithm based on the similarity between local features is also proposed to classify unlabeled data. Experimental results on FERET database prove that the proposed method is robust to expression variations.

AB - Gabor-based face representation has achieved enormous success in face recognition. However, one drawback of Gabor-based face representation is the huge amount of data that must be stored. Due to the nonlinear structure of the data obtained from Gabor response, classical linear projection methods like principal component analysis fail to learn the distribution of the data. A nonlinear projection method based on a set of self-organizing maps is employed to capture this nonlinearity and to represent face in a new reduced feature space. The Multiple Self-Organized Gabor Features (MSOGF) algorithm is used to represent the input image using all winner indices from each SOM map. A new local matching algorithm based on the similarity between local features is also proposed to classify unlabeled data. Experimental results on FERET database prove that the proposed method is robust to expression variations.

UR - http://www.scopus.com/inward/record.url?scp=78149481376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149481376&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2010.713

DO - 10.1109/ICPR.2010.713

M3 - Conference contribution

SN - 9780769541099

SP - 2909

EP - 2912

BT - Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010

ER -