Share Email Print

Proceedings Paper

Analysis of a large set of color spaces for skin pixel detection in color images
Author(s): Jean-Christophe Terrillon; Arnaud Pilpre; Yoshinori Niwa; Kazuhiko Yamamoto
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Human skin color is a powerful fundamental cue that can be used in particular, at an early stage, for the important applications of face and hand detection in color images, and ultimately, for meaningful human-computer interactions. In this paper, we analyze the distribution of human skin for a large number of three-dimensional (3-D) color spaces (or 2-D chrominance spaces) and for skin images recorded with two different camera systems. By use of seven different criteria, we show that mainly the normalized r-g and CIE-xy chrominance spaces, or spaces constructed as a suitable linear combination or as ratios of normalized r, g and b values, or a space normalized by √R2+G2+B2, are consistently the most efficient for skin pixel detection and consequently, for image segmentation based on skin color. In particular, in these spaces the skin distribution can be modeled by a simple, single elliptical Gaussian, and it is most robust to a change of camera system.

Paper Details

Date Published: 1 May 2003
PDF: 14 pages
Proc. SPIE 5132, Sixth International Conference on Quality Control by Artificial Vision, (1 May 2003); doi: 10.1117/12.515148
Show Author Affiliations
Jean-Christophe Terrillon, Softopia Japan (Japan)
Arnaud Pilpre, Softopia Japan (Japan)
Yoshinori Niwa, Softopia Japan (Japan)
Kazuhiko Yamamoto, Gifu Univ. (Japan)

Published in SPIE Proceedings Vol. 5132:
Sixth International Conference on Quality Control by Artificial Vision
Kenneth W. Tobin; Fabrice Meriaudeau, Editor(s)

© SPIE. Terms of Use
Back to Top