ISSN 2630-0583 (Print)

ISSN 2630-0656 (Online)

JCST

Journal of Current Science and Technology

http://jcst.rsu.ac.th

Rangsit Journal of Arts and Sciences. Vol.2 No.1 , January - June 2012.

Asiatic skin color segmentation using an adaptive algorithm in changing luminance environment

Chutisant Kerdvibulvech

Abstract

           Skin color of Asiatic people is a unique color.  Therefore, Asiatic skin color segmentation is not trivial, particularly in non-static background.  This paper proposes a novel algorithm to segment an area of Asiatic skin color effectively.  By using the on-line adaptation of color probabilities, the algorithm proposes two main benefits: it can cope with luminance changes very well, and also it can be processed in real-time. Bayes’ theorem and Bayesian classifier are employed to compute the probability of skin color of Asiatic people.  Representative results from the experiments are presented to show the efficiency of the proposed system.  The system presented can be further used to develop the real-time vision-based applications in many challenging environments.

Keywords: Asiatic skin, color segmentation, Bayes theorem, Bayesian, adaptive algorithm, luminance

Download Full Paper.

DOI: 10.14456/rjas.2012.4