Local contrast enhancement and adaptive feature extraction for illumination-invariant face recognition

Wen Chung Kao, Ming Chai Hsu, Yueh Yiing Yang

Research output: Contribution to journalArticle

54 Citations (Scopus)

Abstract

Recognizing human faces in various lighting conditions is quite a difficult problem. The problem becomes more difficult when face images are taken in extremely high dynamic range scenes. Most of the automatic face recognition systems assume that images are taken under well-controlled illumination. The face segmentation as well as recognition becomes much simpler under such a constrained condition. However, illumination control is not feasible when a surveillance system is installed in any location at will. Without compensating for uneven illumination, it is impossible to get a satisfactory recognition rate. In this paper, we propose an integrated system that first compensates uneven illumination through local contrast enhancement. Then the enhanced images are fed into a robust face recognition system which adaptively selects the most important features among all candidate features and performs classification by support vector machines (SVMs). The dimension of feature space as well as the selected types of features is customized for each hyperplane. Three face image databases, namely Yale, Yale Group B, and Extended Yale Group B, are used to evaluate performance. The experimental result shows that the proposed recognition system give superior results compared to recently published literatures.

Original languageEnglish
Pages (from-to)1736-1747
Number of pages12
JournalPattern Recognition
Volume43
Issue number5
DOIs
Publication statusPublished - 2010 May 1

Fingerprint

Face recognition
Feature extraction
Lighting
Support vector machines

Keywords

  • Adaptive feature selection
  • Face recognition
  • Local contrast enhancement
  • Support vector machines

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Local contrast enhancement and adaptive feature extraction for illumination-invariant face recognition. / Kao, Wen Chung; Hsu, Ming Chai; Yang, Yueh Yiing.

In: Pattern Recognition, Vol. 43, No. 5, 01.05.2010, p. 1736-1747.

Research output: Contribution to journalArticle

@article{b11643530aee4c24b4697797b5cc0760,
title = "Local contrast enhancement and adaptive feature extraction for illumination-invariant face recognition",
abstract = "Recognizing human faces in various lighting conditions is quite a difficult problem. The problem becomes more difficult when face images are taken in extremely high dynamic range scenes. Most of the automatic face recognition systems assume that images are taken under well-controlled illumination. The face segmentation as well as recognition becomes much simpler under such a constrained condition. However, illumination control is not feasible when a surveillance system is installed in any location at will. Without compensating for uneven illumination, it is impossible to get a satisfactory recognition rate. In this paper, we propose an integrated system that first compensates uneven illumination through local contrast enhancement. Then the enhanced images are fed into a robust face recognition system which adaptively selects the most important features among all candidate features and performs classification by support vector machines (SVMs). The dimension of feature space as well as the selected types of features is customized for each hyperplane. Three face image databases, namely Yale, Yale Group B, and Extended Yale Group B, are used to evaluate performance. The experimental result shows that the proposed recognition system give superior results compared to recently published literatures.",
keywords = "Adaptive feature selection, Face recognition, Local contrast enhancement, Support vector machines",
author = "Kao, {Wen Chung} and Hsu, {Ming Chai} and Yang, {Yueh Yiing}",
year = "2010",
month = "5",
day = "1",
doi = "10.1016/j.patcog.2009.11.016",
language = "English",
volume = "43",
pages = "1736--1747",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "5",

}

TY - JOUR

T1 - Local contrast enhancement and adaptive feature extraction for illumination-invariant face recognition

AU - Kao, Wen Chung

AU - Hsu, Ming Chai

AU - Yang, Yueh Yiing

PY - 2010/5/1

Y1 - 2010/5/1

N2 - Recognizing human faces in various lighting conditions is quite a difficult problem. The problem becomes more difficult when face images are taken in extremely high dynamic range scenes. Most of the automatic face recognition systems assume that images are taken under well-controlled illumination. The face segmentation as well as recognition becomes much simpler under such a constrained condition. However, illumination control is not feasible when a surveillance system is installed in any location at will. Without compensating for uneven illumination, it is impossible to get a satisfactory recognition rate. In this paper, we propose an integrated system that first compensates uneven illumination through local contrast enhancement. Then the enhanced images are fed into a robust face recognition system which adaptively selects the most important features among all candidate features and performs classification by support vector machines (SVMs). The dimension of feature space as well as the selected types of features is customized for each hyperplane. Three face image databases, namely Yale, Yale Group B, and Extended Yale Group B, are used to evaluate performance. The experimental result shows that the proposed recognition system give superior results compared to recently published literatures.

AB - Recognizing human faces in various lighting conditions is quite a difficult problem. The problem becomes more difficult when face images are taken in extremely high dynamic range scenes. Most of the automatic face recognition systems assume that images are taken under well-controlled illumination. The face segmentation as well as recognition becomes much simpler under such a constrained condition. However, illumination control is not feasible when a surveillance system is installed in any location at will. Without compensating for uneven illumination, it is impossible to get a satisfactory recognition rate. In this paper, we propose an integrated system that first compensates uneven illumination through local contrast enhancement. Then the enhanced images are fed into a robust face recognition system which adaptively selects the most important features among all candidate features and performs classification by support vector machines (SVMs). The dimension of feature space as well as the selected types of features is customized for each hyperplane. Three face image databases, namely Yale, Yale Group B, and Extended Yale Group B, are used to evaluate performance. The experimental result shows that the proposed recognition system give superior results compared to recently published literatures.

KW - Adaptive feature selection

KW - Face recognition

KW - Local contrast enhancement

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=75749158067&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=75749158067&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2009.11.016

DO - 10.1016/j.patcog.2009.11.016

M3 - Article

AN - SCOPUS:75749158067

VL - 43

SP - 1736

EP - 1747

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 5

ER -