Detecting human faces in color images

Ming Hsuan Yang, Narendra Ahuja

Research output: Contribution to conferencePaper

Abstract

We propose a new method to detect human faces in color images. A human skin color model is built to capture the chromatic properties based on multivariate statistical analysis. Given a color image, multiscale segmentation is used to generate homogeneous regions at multiple different scales. From the coarsest to the finest scale, regions of skin color are merged until the shape is approximately elliptic. Postprocessing is performed to determine whether a merged region contains a human face and include the facial features of non-skin color such as eyes and mouth if necessary. Experimental results show that human faces in color images can be detected regardless of size, orientation and viewpoint.

Original languageEnglish (US)
Pages127-130
Number of pages4
StatePublished - Dec 1 1998
EventProceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3) - Chicago, IL, USA
Duration: Oct 4 1998Oct 7 1998

Other

OtherProceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3)
CityChicago, IL, USA
Period10/4/9810/7/98

Fingerprint

Color
Skin
Image segmentation
Statistical methods

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Yang, M. H., & Ahuja, N. (1998). Detecting human faces in color images. 127-130. Paper presented at Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3), Chicago, IL, USA, .

Detecting human faces in color images. / Yang, Ming Hsuan; Ahuja, Narendra.

1998. 127-130 Paper presented at Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3), Chicago, IL, USA, .

Research output: Contribution to conferencePaper

Yang, MH & Ahuja, N 1998, 'Detecting human faces in color images' Paper presented at Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3), Chicago, IL, USA, 10/4/98 - 10/7/98, pp. 127-130.
Yang MH, Ahuja N. Detecting human faces in color images. 1998. Paper presented at Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3), Chicago, IL, USA, .
Yang, Ming Hsuan ; Ahuja, Narendra. / Detecting human faces in color images. Paper presented at Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3), Chicago, IL, USA, .4 p.
@conference{a68c4e2f20994a4ab060dfd58ef098bf,
title = "Detecting human faces in color images",
abstract = "We propose a new method to detect human faces in color images. A human skin color model is built to capture the chromatic properties based on multivariate statistical analysis. Given a color image, multiscale segmentation is used to generate homogeneous regions at multiple different scales. From the coarsest to the finest scale, regions of skin color are merged until the shape is approximately elliptic. Postprocessing is performed to determine whether a merged region contains a human face and include the facial features of non-skin color such as eyes and mouth if necessary. Experimental results show that human faces in color images can be detected regardless of size, orientation and viewpoint.",
author = "Yang, {Ming Hsuan} and Narendra Ahuja",
year = "1998",
month = "12",
day = "1",
language = "English (US)",
pages = "127--130",
note = "Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3) ; Conference date: 04-10-1998 Through 07-10-1998",

}

TY - CONF

T1 - Detecting human faces in color images

AU - Yang, Ming Hsuan

AU - Ahuja, Narendra

PY - 1998/12/1

Y1 - 1998/12/1

N2 - We propose a new method to detect human faces in color images. A human skin color model is built to capture the chromatic properties based on multivariate statistical analysis. Given a color image, multiscale segmentation is used to generate homogeneous regions at multiple different scales. From the coarsest to the finest scale, regions of skin color are merged until the shape is approximately elliptic. Postprocessing is performed to determine whether a merged region contains a human face and include the facial features of non-skin color such as eyes and mouth if necessary. Experimental results show that human faces in color images can be detected regardless of size, orientation and viewpoint.

AB - We propose a new method to detect human faces in color images. A human skin color model is built to capture the chromatic properties based on multivariate statistical analysis. Given a color image, multiscale segmentation is used to generate homogeneous regions at multiple different scales. From the coarsest to the finest scale, regions of skin color are merged until the shape is approximately elliptic. Postprocessing is performed to determine whether a merged region contains a human face and include the facial features of non-skin color such as eyes and mouth if necessary. Experimental results show that human faces in color images can be detected regardless of size, orientation and viewpoint.

UR - http://www.scopus.com/inward/record.url?scp=0032306424&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032306424&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0032306424

SP - 127

EP - 130

ER -