Gabor feature based classification using Enhance Two-direction Variation of 2DPCA discriminant analysis for face verification

Hsi Kuan Chen, Yi Chun Lee, Chin-Hsing Chen

Research output: Contribution to conferencePaper

8 Citations (Scopus)

Abstract

This paper derives and implements a new technique called horizontal and vertical Enhance Gabor discriminant analysis (HVGD) for image representation and recognition. In this approach, we firstly use Gabor wavelets to extract local features at different frequencies and orientations from facial images. The horizontal and vertical principal component analysis (HVPCA) is then applied directly on the Gabor transformed matrices to reduce sensitivity to imprecise eye detection and face cropping. To improve upon the traditional discriminant analysis methods for face verification, the enhanced Fisher linear discriminant model (EFM) method is finally applied to further remove redundant information and form a discriminant representation more suitable for face recognition. The results show that the HVGD method performs better than the PCA, the FLD, and the EFM. The top recognition accuracy of our proposed method can reach 97.7% on the Yale database.

Original languageEnglish
Pages541-548
Number of pages8
DOIs
Publication statusPublished - 2013 May 27
Event2013 IEEE International Symposium on Next-Generation Electronics, ISNE 2013 - Kaohsiung, Taiwan
Duration: 2013 Feb 252013 Feb 26

Other

Other2013 IEEE International Symposium on Next-Generation Electronics, ISNE 2013
CountryTaiwan
CityKaohsiung
Period13-02-2513-02-26

Fingerprint

Discriminant analysis
Face recognition
Principal component analysis

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Chen, H. K., Lee, Y. C., & Chen, C-H. (2013). Gabor feature based classification using Enhance Two-direction Variation of 2DPCA discriminant analysis for face verification. 541-548. Paper presented at 2013 IEEE International Symposium on Next-Generation Electronics, ISNE 2013, Kaohsiung, Taiwan. https://doi.org/10.1109/ISNE.2013.6512419
Chen, Hsi Kuan ; Lee, Yi Chun ; Chen, Chin-Hsing. / Gabor feature based classification using Enhance Two-direction Variation of 2DPCA discriminant analysis for face verification. Paper presented at 2013 IEEE International Symposium on Next-Generation Electronics, ISNE 2013, Kaohsiung, Taiwan.8 p.
@conference{0755f4d642d146fdb2b993b241f62e71,
title = "Gabor feature based classification using Enhance Two-direction Variation of 2DPCA discriminant analysis for face verification",
abstract = "This paper derives and implements a new technique called horizontal and vertical Enhance Gabor discriminant analysis (HVGD) for image representation and recognition. In this approach, we firstly use Gabor wavelets to extract local features at different frequencies and orientations from facial images. The horizontal and vertical principal component analysis (HVPCA) is then applied directly on the Gabor transformed matrices to reduce sensitivity to imprecise eye detection and face cropping. To improve upon the traditional discriminant analysis methods for face verification, the enhanced Fisher linear discriminant model (EFM) method is finally applied to further remove redundant information and form a discriminant representation more suitable for face recognition. The results show that the HVGD method performs better than the PCA, the FLD, and the EFM. The top recognition accuracy of our proposed method can reach 97.7{\%} on the Yale database.",
author = "Chen, {Hsi Kuan} and Lee, {Yi Chun} and Chin-Hsing Chen",
year = "2013",
month = "5",
day = "27",
doi = "10.1109/ISNE.2013.6512419",
language = "English",
pages = "541--548",
note = "2013 IEEE International Symposium on Next-Generation Electronics, ISNE 2013 ; Conference date: 25-02-2013 Through 26-02-2013",

}

Chen, HK, Lee, YC & Chen, C-H 2013, 'Gabor feature based classification using Enhance Two-direction Variation of 2DPCA discriminant analysis for face verification' Paper presented at 2013 IEEE International Symposium on Next-Generation Electronics, ISNE 2013, Kaohsiung, Taiwan, 13-02-25 - 13-02-26, pp. 541-548. https://doi.org/10.1109/ISNE.2013.6512419

Gabor feature based classification using Enhance Two-direction Variation of 2DPCA discriminant analysis for face verification. / Chen, Hsi Kuan; Lee, Yi Chun; Chen, Chin-Hsing.

2013. 541-548 Paper presented at 2013 IEEE International Symposium on Next-Generation Electronics, ISNE 2013, Kaohsiung, Taiwan.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Gabor feature based classification using Enhance Two-direction Variation of 2DPCA discriminant analysis for face verification

AU - Chen, Hsi Kuan

AU - Lee, Yi Chun

AU - Chen, Chin-Hsing

PY - 2013/5/27

Y1 - 2013/5/27

N2 - This paper derives and implements a new technique called horizontal and vertical Enhance Gabor discriminant analysis (HVGD) for image representation and recognition. In this approach, we firstly use Gabor wavelets to extract local features at different frequencies and orientations from facial images. The horizontal and vertical principal component analysis (HVPCA) is then applied directly on the Gabor transformed matrices to reduce sensitivity to imprecise eye detection and face cropping. To improve upon the traditional discriminant analysis methods for face verification, the enhanced Fisher linear discriminant model (EFM) method is finally applied to further remove redundant information and form a discriminant representation more suitable for face recognition. The results show that the HVGD method performs better than the PCA, the FLD, and the EFM. The top recognition accuracy of our proposed method can reach 97.7% on the Yale database.

AB - This paper derives and implements a new technique called horizontal and vertical Enhance Gabor discriminant analysis (HVGD) for image representation and recognition. In this approach, we firstly use Gabor wavelets to extract local features at different frequencies and orientations from facial images. The horizontal and vertical principal component analysis (HVPCA) is then applied directly on the Gabor transformed matrices to reduce sensitivity to imprecise eye detection and face cropping. To improve upon the traditional discriminant analysis methods for face verification, the enhanced Fisher linear discriminant model (EFM) method is finally applied to further remove redundant information and form a discriminant representation more suitable for face recognition. The results show that the HVGD method performs better than the PCA, the FLD, and the EFM. The top recognition accuracy of our proposed method can reach 97.7% on the Yale database.

UR - http://www.scopus.com/inward/record.url?scp=84877948818&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877948818&partnerID=8YFLogxK

U2 - 10.1109/ISNE.2013.6512419

DO - 10.1109/ISNE.2013.6512419

M3 - Paper

AN - SCOPUS:84877948818

SP - 541

EP - 548

ER -

Chen HK, Lee YC, Chen C-H. Gabor feature based classification using Enhance Two-direction Variation of 2DPCA discriminant analysis for face verification. 2013. Paper presented at 2013 IEEE International Symposium on Next-Generation Electronics, ISNE 2013, Kaohsiung, Taiwan. https://doi.org/10.1109/ISNE.2013.6512419