Centralized Gradient Pattern for Face Recognition

Dong-Ju KIM; Sang-Heon LEE; Myoung-Kyu SHON

doi:10.1587/transinf.E96.D.538

Centralized Gradient Pattern for Face Recognition

Dong-Ju KIM, Sang-Heon LEE, Myoung-Kyu SHON

Full Text Views

0

Cite this

Summary :

This paper proposes a novel face recognition approach using a centralized gradient pattern image and image covariance-based facial feature extraction algorithms, i.e. a two-dimensional principal component analysis and an alternative two-dimensional principal component analysis. The centralized gradient pattern image is obtained by AND operation of a modified center-symmetric local binary pattern image and a modified local directional pattern image, and it is then utilized as input image for the facial feature extraction based on image covariance. To verify the proposed face recognition method, the performance evaluation was carried out using various recognition algorithms on the Yale B, the extended Yale B and the CMU-PIE illumination databases. From the experimental results, the proposed method showed the best recognition accuracy compared to different approaches, and we confirmed that the proposed approach is robust to illumination variation.

Publication: IEICE TRANSACTIONS on Information Vol.E96-D No.3 pp.538-549

Publication Date: 2013/03/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E96.D.538

Type of Manuscript: Special Section PAPER (Special Section on Face Perception and Recognition)

Category: Face Perception and Recognition

Cite this

Copy

Dong-Ju KIM, Sang-Heon LEE, Myoung-Kyu SHON, "Centralized Gradient Pattern for Face Recognition" in IEICE TRANSACTIONS on Information, vol. E96-D, no. 3, pp. 538-549, March 2013, doi: 10.1587/transinf.E96.D.538.
Abstract: This paper proposes a novel face recognition approach using a centralized gradient pattern image and image covariance-based facial feature extraction algorithms, i.e. a two-dimensional principal component analysis and an alternative two-dimensional principal component analysis. The centralized gradient pattern image is obtained by AND operation of a modified center-symmetric local binary pattern image and a modified local directional pattern image, and it is then utilized as input image for the facial feature extraction based on image covariance. To verify the proposed face recognition method, the performance evaluation was carried out using various recognition algorithms on the Yale B, the extended Yale B and the CMU-PIE illumination databases. From the experimental results, the proposed method showed the best recognition accuracy compared to different approaches, and we confirmed that the proposed approach is robust to illumination variation.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.538/_p

Copy

@ARTICLE{e96-d_3_538,
author={Dong-Ju KIM, Sang-Heon LEE, Myoung-Kyu SHON, },
journal={IEICE TRANSACTIONS on Information},
title={Centralized Gradient Pattern for Face Recognition},
year={2013},
volume={E96-D},
number={3},
pages={538-549},
abstract={This paper proposes a novel face recognition approach using a centralized gradient pattern image and image covariance-based facial feature extraction algorithms, i.e. a two-dimensional principal component analysis and an alternative two-dimensional principal component analysis. The centralized gradient pattern image is obtained by AND operation of a modified center-symmetric local binary pattern image and a modified local directional pattern image, and it is then utilized as input image for the facial feature extraction based on image covariance. To verify the proposed face recognition method, the performance evaluation was carried out using various recognition algorithms on the Yale B, the extended Yale B and the CMU-PIE illumination databases. From the experimental results, the proposed method showed the best recognition accuracy compared to different approaches, and we confirmed that the proposed approach is robust to illumination variation.},
keywords={},
doi={10.1587/transinf.E96.D.538},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Centralized Gradient Pattern for Face Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 538
EP - 549
AU - Dong-Ju KIM
AU - Sang-Heon LEE
AU - Myoung-Kyu SHON
PY - 2013
DO - 10.1587/transinf.E96.D.538
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2013
AB - This paper proposes a novel face recognition approach using a centralized gradient pattern image and image covariance-based facial feature extraction algorithms, i.e. a two-dimensional principal component analysis and an alternative two-dimensional principal component analysis. The centralized gradient pattern image is obtained by AND operation of a modified center-symmetric local binary pattern image and a modified local directional pattern image, and it is then utilized as input image for the facial feature extraction based on image covariance. To verify the proposed face recognition method, the performance evaluation was carried out using various recognition algorithms on the Yale B, the extended Yale B and the CMU-PIE illumination databases. From the experimental results, the proposed method showed the best recognition accuracy compared to different approaches, and we confirmed that the proposed approach is robust to illumination variation.
ER -