Contrast compensation by fuzzy classification and image illumination analysis for back-lit and front-lit color face images

Chun Ming Tsai, Zong-Mu Yeh

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Conventional contrast enhancement methods have two shortcomings. First, most of them do not produce satisfactory enhancement results for face images with back-lit or front-lit. Second, most of them need transformation functions and parameters which are specified manually. Thus, this paper proposes an automatic and parameter-free contrast compensation algorithm for skin detection in color face images. This method includes following steps: First, RGB color space is transformed to YIQ color space. Second, fuzzy logic is used to classify the color images into three categories: back-lit, normal-lit, and front-lit. Third, image illumination analysis is used to analyze the image distribution. Fourth, the input image is compensated by piecewise linear based enhancement method. Finally, the compensation image is transformed back to RGB color space. Our experiments included various color and gray face images. Experiment results show that the performance of the proposed compensation method is better than other available methods in skin detection and visual perception measurements.

Original languageEnglish
Article number5606299
Pages (from-to)1570-1578
Number of pages9
JournalIEEE Transactions on Consumer Electronics
Volume56
Issue number3
DOIs
Publication statusPublished - 2010 Aug 1

Fingerprint

Lighting
Color
Skin
Fuzzy logic
Compensation and Redress
Experiments

Keywords

  • Color face images
  • Contrast compensation
  • Fuzzy logic classification
  • Image illumination analysis

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Media Technology

Cite this

Contrast compensation by fuzzy classification and image illumination analysis for back-lit and front-lit color face images. / Tsai, Chun Ming; Yeh, Zong-Mu.

In: IEEE Transactions on Consumer Electronics, Vol. 56, No. 3, 5606299, 01.08.2010, p. 1570-1578.

Research output: Contribution to journalArticle

@article{46117a0ac8d7484ea10f76e39fa8bf6b,
title = "Contrast compensation by fuzzy classification and image illumination analysis for back-lit and front-lit color face images",
abstract = "Conventional contrast enhancement methods have two shortcomings. First, most of them do not produce satisfactory enhancement results for face images with back-lit or front-lit. Second, most of them need transformation functions and parameters which are specified manually. Thus, this paper proposes an automatic and parameter-free contrast compensation algorithm for skin detection in color face images. This method includes following steps: First, RGB color space is transformed to YIQ color space. Second, fuzzy logic is used to classify the color images into three categories: back-lit, normal-lit, and front-lit. Third, image illumination analysis is used to analyze the image distribution. Fourth, the input image is compensated by piecewise linear based enhancement method. Finally, the compensation image is transformed back to RGB color space. Our experiments included various color and gray face images. Experiment results show that the performance of the proposed compensation method is better than other available methods in skin detection and visual perception measurements.",
keywords = "Color face images, Contrast compensation, Fuzzy logic classification, Image illumination analysis",
author = "Tsai, {Chun Ming} and Zong-Mu Yeh",
year = "2010",
month = "8",
day = "1",
doi = "10.1109/TCE.2010.5606299",
language = "English",
volume = "56",
pages = "1570--1578",
journal = "IEEE Transactions on Consumer Electronics",
issn = "0098-3063",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Contrast compensation by fuzzy classification and image illumination analysis for back-lit and front-lit color face images

AU - Tsai, Chun Ming

AU - Yeh, Zong-Mu

PY - 2010/8/1

Y1 - 2010/8/1

N2 - Conventional contrast enhancement methods have two shortcomings. First, most of them do not produce satisfactory enhancement results for face images with back-lit or front-lit. Second, most of them need transformation functions and parameters which are specified manually. Thus, this paper proposes an automatic and parameter-free contrast compensation algorithm for skin detection in color face images. This method includes following steps: First, RGB color space is transformed to YIQ color space. Second, fuzzy logic is used to classify the color images into three categories: back-lit, normal-lit, and front-lit. Third, image illumination analysis is used to analyze the image distribution. Fourth, the input image is compensated by piecewise linear based enhancement method. Finally, the compensation image is transformed back to RGB color space. Our experiments included various color and gray face images. Experiment results show that the performance of the proposed compensation method is better than other available methods in skin detection and visual perception measurements.

AB - Conventional contrast enhancement methods have two shortcomings. First, most of them do not produce satisfactory enhancement results for face images with back-lit or front-lit. Second, most of them need transformation functions and parameters which are specified manually. Thus, this paper proposes an automatic and parameter-free contrast compensation algorithm for skin detection in color face images. This method includes following steps: First, RGB color space is transformed to YIQ color space. Second, fuzzy logic is used to classify the color images into three categories: back-lit, normal-lit, and front-lit. Third, image illumination analysis is used to analyze the image distribution. Fourth, the input image is compensated by piecewise linear based enhancement method. Finally, the compensation image is transformed back to RGB color space. Our experiments included various color and gray face images. Experiment results show that the performance of the proposed compensation method is better than other available methods in skin detection and visual perception measurements.

KW - Color face images

KW - Contrast compensation

KW - Fuzzy logic classification

KW - Image illumination analysis

UR - http://www.scopus.com/inward/record.url?scp=78149238806&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149238806&partnerID=8YFLogxK

U2 - 10.1109/TCE.2010.5606299

DO - 10.1109/TCE.2010.5606299

M3 - Article

VL - 56

SP - 1570

EP - 1578

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

SN - 0098-3063

IS - 3

M1 - 5606299

ER -