Title

Adaptive Skin Segmentation in Color Images

Document Type

Conference Proceeding

Publisher

IEEE

Faculty

Computing, Health and Science

School

Engineering and Mathematics, Centre for Communications Engineering Research

RAS ID

1391

Comments

This article was originally published as: Phung, S. L., Chai, D. K., & Bouzerdoum, A. (2003). Adaptive skin segmentation in color images. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing. (pp. VIII-353-6). Piscataway, NJ. IEEE. Original article available here

Abstract

A new skin segmentation technique for color images is proposed. The proposed technique uses a human skin color model that is based on the Bayesian decision theory and developed using a large training set of skin colors and nonskin colors. The proposed technique is novel and unique in that texture characteristics of the human skin are used to select appropriate skin color thresholds for skin segmentation. Two homogeneity measures for skin regions that take into account both global and local image features are also proposed. Experimental results showed that the proposed technique can achieve good skin segmentation performance (false detection rate of 4.5% and false rejection rate of 4.0%).

 

Link to publisher version (DOI)

10.1109/ICASSP.2003.1199483