Title: Adaptive method for improvement of human skin detection in colour images

Authors: Frederico Grilo; João Figueiredo; Octavio Dias

Addresses: CEM – University of Évora and the Electrical Engineering Department, EST Setubal/IPS, CESET, Portugal ' CEM-IDMEC, University of Evora, Centre of Mechatronics Engineering, R. Romao Ramalho, 59, 7000-671 Evora, Portugal ' Electrical Engineering Department, EST Setubal/IPS, CESET, INESC, Department of Information & Technology, Setubal/IPS, CESET, Portugal

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.

Keywords: adaptive algorithms; image processing; skin detection; human skin; colour images; skin classifiers; face detection.

DOI: 10.1504/IJCAT.2014.059091

International Journal of Computer Applications in Technology, 2014 Vol.49 No.1, pp.1 - 11

Received: 08 May 2021
Accepted: 12 May 2021

Published online: 03 Feb 2014 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article