Adaptive method for improvement of human skin detection in colour images
by Frederico Grilo; João Figueiredo; Octavio Dias
International Journal of Computer Applications in Technology (IJCAT), Vol. 49, No. 1, 2014

Abstract: In this paper, a new approach to detect human skin in colour images is proposed. The method uses the classification of the three colour components of the RGB system (red, green and blue), with a new approach to skin classifiers and face detection. The developed approach uses an adaptive methodology embedded in the skin classifier algorithm and a new face detection method to determine the location of the face in the image, improving the detection of the skin pixels and, therefore, reducing simultaneously the computational burden. The developed adaptive method varies the parameters of the base detection algorithm, for each one of the RGB colour components, to reduce the influence of external disturbances, namely the different illumination conditions. Experimental tests validate the proposed methodology showing very good results, in terms of skin detection with very different characteristics in face morphology, different backgrounds and illumination conditions.

Online publication date: Fri, 11-Jul-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Applications in Technology (IJCAT):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com