Analysis of Noteworthy Issues in Illumination Processing for Face Recognition

Min YAO; Hiroshi NAGAHASHI

doi:10.1587/transinf.2014EDP7112

Analysis of Noteworthy Issues in Illumination Processing for Face Recognition

Min YAO, Hiroshi NAGAHASHI

Full Text Views

0

Share
Cite this

Summary :

Face recognition under variable illumination conditions is a challenging task. Numbers of approaches have been developed for solving the illumination problem. In this paper, we summarize and analyze some noteworthy issues in illumination processing for face recognition by reviewing various representative approaches. These issues include a principle that associates various approaches with a commonly used reflectance model and the shared considerations like contribution of basic processing methods, processing domain, feature scale, and a common problem. We also address a more essential question-what to actually normalize. Through the discussion on these issues, we also provide suggestions on potential directions for future research. In addition, we conduct evaluation experiments on 1) contribution of fundamental illumination correction to illumination insensitive face recognition and 2) comparative performance of various approaches. Experimental results show that the approaches with fundamental illumination correction methods are more insensitive to extreme illumination than without them. Tan and Triggs' method (TT) using L₁ norm achieves the best results among nine tested approaches.

Publication: IEICE TRANSACTIONS on Information Vol.E98-D No.3 pp.681-691

Publication Date: 2015/03/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2014EDP7112

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Authors

Min YAO
Shanghai Maritime University
Hiroshi NAGAHASHI
Tokyo Institute of Technology

Keyword

face recognition, illumination processing, noteworthy issues, analysis, evaluation

Cite this

Copy

Min YAO, Hiroshi NAGAHASHI, "Analysis of Noteworthy Issues in Illumination Processing for Face Recognition" in IEICE TRANSACTIONS on Information, vol. E98-D, no. 3, pp. 681-691, March 2015, doi: 10.1587/transinf.2014EDP7112.
Abstract: Face recognition under variable illumination conditions is a challenging task. Numbers of approaches have been developed for solving the illumination problem. In this paper, we summarize and analyze some noteworthy issues in illumination processing for face recognition by reviewing various representative approaches. These issues include a principle that associates various approaches with a commonly used reflectance model and the shared considerations like contribution of basic processing methods, processing domain, feature scale, and a common problem. We also address a more essential question-what to actually normalize. Through the discussion on these issues, we also provide suggestions on potential directions for future research. In addition, we conduct evaluation experiments on 1) contribution of fundamental illumination correction to illumination insensitive face recognition and 2) comparative performance of various approaches. Experimental results show that the approaches with fundamental illumination correction methods are more insensitive to extreme illumination than without them. Tan and Triggs' method (TT) using L₁ norm achieves the best results among nine tested approaches.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2014EDP7112/_p

Copy

@ARTICLE{e98-d_3_681,
author={Min YAO, Hiroshi NAGAHASHI, },
journal={IEICE TRANSACTIONS on Information},
title={Analysis of Noteworthy Issues in Illumination Processing for Face Recognition},
year={2015},
volume={E98-D},
number={3},
pages={681-691},
abstract={Face recognition under variable illumination conditions is a challenging task. Numbers of approaches have been developed for solving the illumination problem. In this paper, we summarize and analyze some noteworthy issues in illumination processing for face recognition by reviewing various representative approaches. These issues include a principle that associates various approaches with a commonly used reflectance model and the shared considerations like contribution of basic processing methods, processing domain, feature scale, and a common problem. We also address a more essential question-what to actually normalize. Through the discussion on these issues, we also provide suggestions on potential directions for future research. In addition, we conduct evaluation experiments on 1) contribution of fundamental illumination correction to illumination insensitive face recognition and 2) comparative performance of various approaches. Experimental results show that the approaches with fundamental illumination correction methods are more insensitive to extreme illumination than without them. Tan and Triggs' method (TT) using L₁ norm achieves the best results among nine tested approaches.},
keywords={},
doi={10.1587/transinf.2014EDP7112},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Analysis of Noteworthy Issues in Illumination Processing for Face Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 681
EP - 691
AU - Min YAO
AU - Hiroshi NAGAHASHI
PY - 2015
DO - 10.1587/transinf.2014EDP7112
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2015
AB - Face recognition under variable illumination conditions is a challenging task. Numbers of approaches have been developed for solving the illumination problem. In this paper, we summarize and analyze some noteworthy issues in illumination processing for face recognition by reviewing various representative approaches. These issues include a principle that associates various approaches with a commonly used reflectance model and the shared considerations like contribution of basic processing methods, processing domain, feature scale, and a common problem. We also address a more essential question-what to actually normalize. Through the discussion on these issues, we also provide suggestions on potential directions for future research. In addition, we conduct evaluation experiments on 1) contribution of fundamental illumination correction to illumination insensitive face recognition and 2) comparative performance of various approaches. Experimental results show that the approaches with fundamental illumination correction methods are more insensitive to extreme illumination than without them. Tan and Triggs' method (TT) using L₁ norm achieves the best results among nine tested approaches.
ER -