Region-based and content adaptive skin detection in color images

Wei Che Chen, Ming-Shi Wang

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Skin detection plays an important role in applications such as face detection and tracking, person detection and pornography detection. While previous studies focus on pixel-based skin color detection techniques that individually classify each pixel as skin color or non-skin color, this study presents a region-based algorithm for detecting skin color. The proposed algorithm uses a special region, called key skin region, as the basis to classify skin color. A performance comparison with conventional skin classifiers, including the Bayesian classifier, the unimodal Gaussian classifier and the Gaussian mixture classifier, is made in this study. Experimental results show that the proposed algorithm outperforms other tested skin classifiers. Furthermore, the skin regions detected by the proposed algorithm, especially facial regions, are nearly complete with no hollow holes in these regions. This property can simplify the complexity of implementing applications that use skin color as their basis, such as face detection and face tracking.

Original languageEnglish
Pages (from-to)831-853
Number of pages23
JournalInternational Journal of Pattern Recognition and Artificial Intelligence
Volume21
Issue number5
DOIs
Publication statusPublished - 2007 Aug 1

Fingerprint

Skin
Color
Classifiers
Face recognition
Pixels

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

@article{b2af9406bb134c78861ed7f004c2fc08,
title = "Region-based and content adaptive skin detection in color images",
abstract = "Skin detection plays an important role in applications such as face detection and tracking, person detection and pornography detection. While previous studies focus on pixel-based skin color detection techniques that individually classify each pixel as skin color or non-skin color, this study presents a region-based algorithm for detecting skin color. The proposed algorithm uses a special region, called key skin region, as the basis to classify skin color. A performance comparison with conventional skin classifiers, including the Bayesian classifier, the unimodal Gaussian classifier and the Gaussian mixture classifier, is made in this study. Experimental results show that the proposed algorithm outperforms other tested skin classifiers. Furthermore, the skin regions detected by the proposed algorithm, especially facial regions, are nearly complete with no hollow holes in these regions. This property can simplify the complexity of implementing applications that use skin color as their basis, such as face detection and face tracking.",
author = "Chen, {Wei Che} and Ming-Shi Wang",
year = "2007",
month = "8",
day = "1",
doi = "10.1142/S0218001407005715",
language = "English",
volume = "21",
pages = "831--853",
journal = "International Journal of Pattern Recognition and Artificial Intelligence",
issn = "0218-0014",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "5",

}

Region-based and content adaptive skin detection in color images. / Chen, Wei Che; Wang, Ming-Shi.

In: International Journal of Pattern Recognition and Artificial Intelligence, Vol. 21, No. 5, 01.08.2007, p. 831-853.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Region-based and content adaptive skin detection in color images

AU - Chen, Wei Che

AU - Wang, Ming-Shi

PY - 2007/8/1

Y1 - 2007/8/1

N2 - Skin detection plays an important role in applications such as face detection and tracking, person detection and pornography detection. While previous studies focus on pixel-based skin color detection techniques that individually classify each pixel as skin color or non-skin color, this study presents a region-based algorithm for detecting skin color. The proposed algorithm uses a special region, called key skin region, as the basis to classify skin color. A performance comparison with conventional skin classifiers, including the Bayesian classifier, the unimodal Gaussian classifier and the Gaussian mixture classifier, is made in this study. Experimental results show that the proposed algorithm outperforms other tested skin classifiers. Furthermore, the skin regions detected by the proposed algorithm, especially facial regions, are nearly complete with no hollow holes in these regions. This property can simplify the complexity of implementing applications that use skin color as their basis, such as face detection and face tracking.

AB - Skin detection plays an important role in applications such as face detection and tracking, person detection and pornography detection. While previous studies focus on pixel-based skin color detection techniques that individually classify each pixel as skin color or non-skin color, this study presents a region-based algorithm for detecting skin color. The proposed algorithm uses a special region, called key skin region, as the basis to classify skin color. A performance comparison with conventional skin classifiers, including the Bayesian classifier, the unimodal Gaussian classifier and the Gaussian mixture classifier, is made in this study. Experimental results show that the proposed algorithm outperforms other tested skin classifiers. Furthermore, the skin regions detected by the proposed algorithm, especially facial regions, are nearly complete with no hollow holes in these regions. This property can simplify the complexity of implementing applications that use skin color as their basis, such as face detection and face tracking.

UR - http://www.scopus.com/inward/record.url?scp=34547820208&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547820208&partnerID=8YFLogxK

U2 - 10.1142/S0218001407005715

DO - 10.1142/S0218001407005715

M3 - Article

VL - 21

SP - 831

EP - 853

JO - International Journal of Pattern Recognition and Artificial Intelligence

JF - International Journal of Pattern Recognition and Artificial Intelligence

SN - 0218-0014

IS - 5

ER -