Statistical classification of skin color pixels from MPEG videos

Jinchang Ren, J. Jiang

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

Detection and classification of skin regions plays important roles in many image processing and vision applications. In this paper, we present a statistical approach for fast skin detection in MPEG-compressed videos. Firstly, conditional probabilities of skin and non-skin pixels are extracted from manual marked training images. Then, candidate skin pixels are identified using the Bayesian maximum a posteriori decision rule. An optimal threshold is then obtained by analyzing of probability error on the basis of the likelihood ratio histogram of skin and non-skin pixels. Experiments from sequences with varying illuminations have demonstrated the effectiveness of our approach
LanguageEnglish
Title of host publicationAdvanced concepts for intelligent vision systems, proceedings
EditorsJ B Talon, W Philips, D Popescu, P Scheunders
Place of PublicationBerlin
PublisherSpringer
Pages395-405
Number of pages10
ISBN (Print)9783540746065
DOIs
Publication statusPublished - 2007

Publication series

NameLecture notes in computer science
PublisherSpringer
Volume4678
ISSN (Print)0302-9743

Fingerprint

Skin
Pixels
Color
Image processing
Lighting
Experiments

Keywords

  • face detection
  • images
  • segmentation

Cite this

Ren, J., & Jiang , J. (2007). Statistical classification of skin color pixels from MPEG videos. In J. B. Talon, W. Philips, D. Popescu, & P. Scheunders (Eds.), Advanced concepts for intelligent vision systems, proceedings (pp. 395-405). (Lecture notes in computer science ; Vol. 4678). Berlin: Springer. https://doi.org/10.1007/978-3-540-74607-2_36
Ren, Jinchang ; Jiang , J. / Statistical classification of skin color pixels from MPEG videos. Advanced concepts for intelligent vision systems, proceedings . editor / J B Talon ; W Philips ; D Popescu ; P Scheunders. Berlin : Springer, 2007. pp. 395-405 (Lecture notes in computer science ).
@inbook{8e30754d88c140bdaac264badb2a0fbc,
title = "Statistical classification of skin color pixels from MPEG videos",
abstract = "Detection and classification of skin regions plays important roles in many image processing and vision applications. In this paper, we present a statistical approach for fast skin detection in MPEG-compressed videos. Firstly, conditional probabilities of skin and non-skin pixels are extracted from manual marked training images. Then, candidate skin pixels are identified using the Bayesian maximum a posteriori decision rule. An optimal threshold is then obtained by analyzing of probability error on the basis of the likelihood ratio histogram of skin and non-skin pixels. Experiments from sequences with varying illuminations have demonstrated the effectiveness of our approach",
keywords = "face detection, images, segmentation",
author = "Jinchang Ren and J. Jiang",
year = "2007",
doi = "10.1007/978-3-540-74607-2_36",
language = "English",
isbn = "9783540746065",
series = "Lecture notes in computer science",
publisher = "Springer",
pages = "395--405",
editor = "Talon, {J B} and W Philips and Popescu, {D } and Scheunders, {P }",
booktitle = "Advanced concepts for intelligent vision systems, proceedings",

}

Ren, J & Jiang , J 2007, Statistical classification of skin color pixels from MPEG videos. in JB Talon, W Philips, D Popescu & P Scheunders (eds), Advanced concepts for intelligent vision systems, proceedings . Lecture notes in computer science , vol. 4678, Springer, Berlin, pp. 395-405. https://doi.org/10.1007/978-3-540-74607-2_36

Statistical classification of skin color pixels from MPEG videos. / Ren, Jinchang; Jiang , J.

Advanced concepts for intelligent vision systems, proceedings . ed. / J B Talon; W Philips; D Popescu; P Scheunders. Berlin : Springer, 2007. p. 395-405 (Lecture notes in computer science ; Vol. 4678).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Statistical classification of skin color pixels from MPEG videos

AU - Ren, Jinchang

AU - Jiang , J.

PY - 2007

Y1 - 2007

N2 - Detection and classification of skin regions plays important roles in many image processing and vision applications. In this paper, we present a statistical approach for fast skin detection in MPEG-compressed videos. Firstly, conditional probabilities of skin and non-skin pixels are extracted from manual marked training images. Then, candidate skin pixels are identified using the Bayesian maximum a posteriori decision rule. An optimal threshold is then obtained by analyzing of probability error on the basis of the likelihood ratio histogram of skin and non-skin pixels. Experiments from sequences with varying illuminations have demonstrated the effectiveness of our approach

AB - Detection and classification of skin regions plays important roles in many image processing and vision applications. In this paper, we present a statistical approach for fast skin detection in MPEG-compressed videos. Firstly, conditional probabilities of skin and non-skin pixels are extracted from manual marked training images. Then, candidate skin pixels are identified using the Bayesian maximum a posteriori decision rule. An optimal threshold is then obtained by analyzing of probability error on the basis of the likelihood ratio histogram of skin and non-skin pixels. Experiments from sequences with varying illuminations have demonstrated the effectiveness of our approach

KW - face detection

KW - images

KW - segmentation

U2 - 10.1007/978-3-540-74607-2_36

DO - 10.1007/978-3-540-74607-2_36

M3 - Chapter

SN - 9783540746065

T3 - Lecture notes in computer science

SP - 395

EP - 405

BT - Advanced concepts for intelligent vision systems, proceedings

A2 - Talon, J B

A2 - Philips, W

A2 - Popescu, D

A2 - Scheunders, P

PB - Springer

CY - Berlin

ER -

Ren J, Jiang J. Statistical classification of skin color pixels from MPEG videos. In Talon JB, Philips W, Popescu D, Scheunders P, editors, Advanced concepts for intelligent vision systems, proceedings . Berlin: Springer. 2007. p. 395-405. (Lecture notes in computer science ). https://doi.org/10.1007/978-3-540-74607-2_36