Gaussian mixture model for human skin color and its applications in image and video databases

Ming Hsuan Yang, Narendra Ahuja

Research output: Contribution to journalConference article

212 Citations (Scopus)

Abstract

This paper is concerned with estimating a probability density function of human skin color using a finite Gaussian mixture model whose parameters are estimated through the EM algorithm. Hawkins' statistical test on the normality and homoscedasticity (common covariance matrix) of the estimated Gaussian mixture models is performed and McLachlan's bootstrap method is used to test the number of components in a mixture. Experimental results show that the estimated Gaussian mixture model fits skin images from a large database. Applications of the estimated density function in image and video databases are presented.

Original languageEnglish
Pages (from-to)458-466
Number of pages9
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume3656
Publication statusPublished - 1999 Jan 1
EventProceedings of the 1999 7th Conference of the Storage and Retrieval for Image and Video Databases VII - San Jose, Ca, USA
Duration: 1999 Jan 261999 Jan 29

Fingerprint

Video Databases
Image Database
Gaussian Mixture Model
Skin
Color
color
Homoscedasticity
Probability density function
Finite Mixture Models
Bootstrap Method
Number of Components
EM Algorithm
Statistical test
normality
Density Function
Normality
statistical tests
Covariance matrix
Statistical tests
probability density functions

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

@article{ba9e5a1c5674435a966287f499656b96,
title = "Gaussian mixture model for human skin color and its applications in image and video databases",
abstract = "This paper is concerned with estimating a probability density function of human skin color using a finite Gaussian mixture model whose parameters are estimated through the EM algorithm. Hawkins' statistical test on the normality and homoscedasticity (common covariance matrix) of the estimated Gaussian mixture models is performed and McLachlan's bootstrap method is used to test the number of components in a mixture. Experimental results show that the estimated Gaussian mixture model fits skin images from a large database. Applications of the estimated density function in image and video databases are presented.",
author = "Yang, {Ming Hsuan} and Narendra Ahuja",
year = "1999",
month = "1",
day = "1",
language = "English",
volume = "3656",
pages = "458--466",
journal = "Proceedings of SPIE - The International Society for Optical Engineering",
issn = "0277-786X",
publisher = "SPIE",

}

Gaussian mixture model for human skin color and its applications in image and video databases. / Yang, Ming Hsuan; Ahuja, Narendra.

In: Proceedings of SPIE - The International Society for Optical Engineering, Vol. 3656, 01.01.1999, p. 458-466.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Gaussian mixture model for human skin color and its applications in image and video databases

AU - Yang, Ming Hsuan

AU - Ahuja, Narendra

PY - 1999/1/1

Y1 - 1999/1/1

N2 - This paper is concerned with estimating a probability density function of human skin color using a finite Gaussian mixture model whose parameters are estimated through the EM algorithm. Hawkins' statistical test on the normality and homoscedasticity (common covariance matrix) of the estimated Gaussian mixture models is performed and McLachlan's bootstrap method is used to test the number of components in a mixture. Experimental results show that the estimated Gaussian mixture model fits skin images from a large database. Applications of the estimated density function in image and video databases are presented.

AB - This paper is concerned with estimating a probability density function of human skin color using a finite Gaussian mixture model whose parameters are estimated through the EM algorithm. Hawkins' statistical test on the normality and homoscedasticity (common covariance matrix) of the estimated Gaussian mixture models is performed and McLachlan's bootstrap method is used to test the number of components in a mixture. Experimental results show that the estimated Gaussian mixture model fits skin images from a large database. Applications of the estimated density function in image and video databases are presented.

UR - http://www.scopus.com/inward/record.url?scp=0032663394&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032663394&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0032663394

VL - 3656

SP - 458

EP - 466

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

ER -