In order to overcome the drawback of TVQI and to utilize the property of dimensionality increasing techniques, a novel model for Kernel TV-based Quotient Image employing Gabor analysis is proposed and applied to face recognition with only one sample per subject. To deal with illumination outliers, an enhanced TV-based quotient image (ETVQI) model is first adopted. Then for preprocessed images by ETVQI, a bank of Gabor filters is built to extract features at specified scales and orientations. Lastly, KPCA is introduced to extract final high-order and nonlinear features of extracted Gabor features. According to experiments on the CAS-PEAL face database, our model could outperform Gabor-based KPCA, TVQI and Gabor-based TVQI when they face most outliers (illumination, expression, masking etc.).
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
GaoYun AN, JiYing WU, QiuQi RUAN, "Kernel TV-Based Quotient Image Employing Gabor Analysis and Its Application to Face Recognition" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 5, pp. 1573-1576, May 2008, doi: 10.1093/ietisy/e91-d.5.1573.
Abstract: In order to overcome the drawback of TVQI and to utilize the property of dimensionality increasing techniques, a novel model for Kernel TV-based Quotient Image employing Gabor analysis is proposed and applied to face recognition with only one sample per subject. To deal with illumination outliers, an enhanced TV-based quotient image (ETVQI) model is first adopted. Then for preprocessed images by ETVQI, a bank of Gabor filters is built to extract features at specified scales and orientations. Lastly, KPCA is introduced to extract final high-order and nonlinear features of extracted Gabor features. According to experiments on the CAS-PEAL face database, our model could outperform Gabor-based KPCA, TVQI and Gabor-based TVQI when they face most outliers (illumination, expression, masking etc.).
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.5.1573/_p
Copy
@ARTICLE{e91-d_5_1573,
author={GaoYun AN, JiYing WU, QiuQi RUAN, },
journal={IEICE TRANSACTIONS on Information},
title={Kernel TV-Based Quotient Image Employing Gabor Analysis and Its Application to Face Recognition},
year={2008},
volume={E91-D},
number={5},
pages={1573-1576},
abstract={In order to overcome the drawback of TVQI and to utilize the property of dimensionality increasing techniques, a novel model for Kernel TV-based Quotient Image employing Gabor analysis is proposed and applied to face recognition with only one sample per subject. To deal with illumination outliers, an enhanced TV-based quotient image (ETVQI) model is first adopted. Then for preprocessed images by ETVQI, a bank of Gabor filters is built to extract features at specified scales and orientations. Lastly, KPCA is introduced to extract final high-order and nonlinear features of extracted Gabor features. According to experiments on the CAS-PEAL face database, our model could outperform Gabor-based KPCA, TVQI and Gabor-based TVQI when they face most outliers (illumination, expression, masking etc.).},
keywords={},
doi={10.1093/ietisy/e91-d.5.1573},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Kernel TV-Based Quotient Image Employing Gabor Analysis and Its Application to Face Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1573
EP - 1576
AU - GaoYun AN
AU - JiYing WU
AU - QiuQi RUAN
PY - 2008
DO - 10.1093/ietisy/e91-d.5.1573
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2008
AB - In order to overcome the drawback of TVQI and to utilize the property of dimensionality increasing techniques, a novel model for Kernel TV-based Quotient Image employing Gabor analysis is proposed and applied to face recognition with only one sample per subject. To deal with illumination outliers, an enhanced TV-based quotient image (ETVQI) model is first adopted. Then for preprocessed images by ETVQI, a bank of Gabor filters is built to extract features at specified scales and orientations. Lastly, KPCA is introduced to extract final high-order and nonlinear features of extracted Gabor features. According to experiments on the CAS-PEAL face database, our model could outperform Gabor-based KPCA, TVQI and Gabor-based TVQI when they face most outliers (illumination, expression, masking etc.).
ER -