Illumination Normalization for Face Recognition Using Energy Minimization Framework

Xiaoguang TU; Feng YANG; Mei XIE; Zheng MA

doi:10.1587/transinf.2016EDL8221

Illumination Normalization for Face Recognition Using Energy Minimization Framework

Xiaoguang TU, Feng YANG, Mei XIE, Zheng MA

Full Text Views

0

Share
Cite this

Summary :

Numerous methods have been developed to handle lighting variations in the preprocessing step of face recognition. However, most of them only use the high-frequency information (edges, lines, corner, etc.) for recognition, as pixels lied in these areas have higher local variance values, and thus insensitive to illumination variations. In this case, information of low-frequency may be discarded and some of the features which are helpful for recognition may be ignored. In this paper, we present a new and efficient method for illumination normalization using an energy minimization framework. The proposed method aims to remove the illumination field of the observed face images while simultaneously preserving the intrinsic facial features. The normalized face image and illumination field could be achieved by a reciprocal iteration scheme. Experiments on CMU-PIE and the Extended Yale B databases show that the proposed method can preserve a very good visual quality even on the images illuminated with deep shadow and high brightness regions, and obtain promising illumination normalization results for better face recognition performance.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.6 pp.1376-1379

Publication Date: 2017/06/01

Publicized: 2017/03/10

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016EDL8221

Type of Manuscript: LETTER

Category: Artificial Intelligence, Data Mining

Authors

Xiaoguang TU
  University of Electronic Science and Technology of China
Feng YANG
  Wenzhou Medical University
Mei XIE
  University of Electronic Science and Technology of China
Zheng MA
  University of Electronic Science and Technology of China

Keyword

energy minimization, illumination normalization, face recognition

Cite this

Copy

Xiaoguang TU, Feng YANG, Mei XIE, Zheng MA, "Illumination Normalization for Face Recognition Using Energy Minimization Framework" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 6, pp. 1376-1379, June 2017, doi: 10.1587/transinf.2016EDL8221.
Abstract: Numerous methods have been developed to handle lighting variations in the preprocessing step of face recognition. However, most of them only use the high-frequency information (edges, lines, corner, etc.) for recognition, as pixels lied in these areas have higher local variance values, and thus insensitive to illumination variations. In this case, information of low-frequency may be discarded and some of the features which are helpful for recognition may be ignored. In this paper, we present a new and efficient method for illumination normalization using an energy minimization framework. The proposed method aims to remove the illumination field of the observed face images while simultaneously preserving the intrinsic facial features. The normalized face image and illumination field could be achieved by a reciprocal iteration scheme. Experiments on CMU-PIE and the Extended Yale B databases show that the proposed method can preserve a very good visual quality even on the images illuminated with deep shadow and high brightness regions, and obtain promising illumination normalization results for better face recognition performance.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8221/_p

Copy

@ARTICLE{e100-d_6_1376,
author={Xiaoguang TU, Feng YANG, Mei XIE, Zheng MA, },
journal={IEICE TRANSACTIONS on Information},
title={Illumination Normalization for Face Recognition Using Energy Minimization Framework},
year={2017},
volume={E100-D},
number={6},
pages={1376-1379},
abstract={Numerous methods have been developed to handle lighting variations in the preprocessing step of face recognition. However, most of them only use the high-frequency information (edges, lines, corner, etc.) for recognition, as pixels lied in these areas have higher local variance values, and thus insensitive to illumination variations. In this case, information of low-frequency may be discarded and some of the features which are helpful for recognition may be ignored. In this paper, we present a new and efficient method for illumination normalization using an energy minimization framework. The proposed method aims to remove the illumination field of the observed face images while simultaneously preserving the intrinsic facial features. The normalized face image and illumination field could be achieved by a reciprocal iteration scheme. Experiments on CMU-PIE and the Extended Yale B databases show that the proposed method can preserve a very good visual quality even on the images illuminated with deep shadow and high brightness regions, and obtain promising illumination normalization results for better face recognition performance.},
keywords={},
doi={10.1587/transinf.2016EDL8221},
ISSN={1745-1361},
month={June},}

Copy

TY - JOUR
TI - Illumination Normalization for Face Recognition Using Energy Minimization Framework
T2 - IEICE TRANSACTIONS on Information
SP - 1376
EP - 1379
AU - Xiaoguang TU
AU - Feng YANG
AU - Mei XIE
AU - Zheng MA
PY - 2017
DO - 10.1587/transinf.2016EDL8221
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2017
AB - Numerous methods have been developed to handle lighting variations in the preprocessing step of face recognition. However, most of them only use the high-frequency information (edges, lines, corner, etc.) for recognition, as pixels lied in these areas have higher local variance values, and thus insensitive to illumination variations. In this case, information of low-frequency may be discarded and some of the features which are helpful for recognition may be ignored. In this paper, we present a new and efficient method for illumination normalization using an energy minimization framework. The proposed method aims to remove the illumination field of the observed face images while simultaneously preserving the intrinsic facial features. The normalized face image and illumination field could be achieved by a reciprocal iteration scheme. Experiments on CMU-PIE and the Extended Yale B databases show that the proposed method can preserve a very good visual quality even on the images illuminated with deep shadow and high brightness regions, and obtain promising illumination normalization results for better face recognition performance.
ER -