Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Skin colour correction and faces detection techniques based on HSL and R colour components

Skin colour correction and faces detection techniques based on HSL and R colour components Human face detection is the first step towards face recognition, video surveillance and bioinformatics applications. The first step in faces detection is skin colour detection. Skincolour detection in visible spectrum is a very challenging task as the skin colour in an image is sensitive to various factors such as sensor characteristics, illumination, optics and ethnicity. Many researchers emphasise that there is a relationship between surface colours and illumination which is closely related problem of colour constancy. Colour correction stage should come first before applying skin colour detection to get better recognition rate. In this paper, a new approach Illumination Reflection Problem (IRP) has been proposed to correct the skin colour in the image that suffers from illumination reflection problem. IRP approach succeeded to correct the colour of 95% of affected pixels from illumination reflection problem. Also, a new approach to solve colour constancy problem is proposed named MMCrCb (Mean of Medians of Cr Cb). The purpose of this correction approach is to prepare the image prior to applying skin detection technique. Its methodology based on transforming the image to YCbCr then correcting the values of Y, Cb and Cr. After doing correction, transform the image back to RGB. Images from Caltech Image Database that suffer from colour constancy problem were used to test the MMCrCb approach. Also nine skin colour detection techniques were investigated and compared with a new proposed technique for skin detection using HSL and R colour components. The data base used for testing that approach was the MUCT database. The MUCT database provides more diversity of lighting, age and ethnicity. The testing results proved that the proposed skin detection technique using HSL and R is the best among techniques in the literature. In addition to that, the use of MMCrCb colour constancy correction approach with the proposed skin detection technique increases the skin colour pixels classification rate of unbalanced colour images by 20%. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Signal and Imaging Systems Engineering Inderscience Publishers

Skin colour correction and faces detection techniques based on HSL and R colour components

Download PDF
12 pages

Loading next page...
 
/lp/inderscience-publishers/skin-colour-correction-and-faces-detection-techniques-based-on-hsl-and-fmmFagIGzV

References (39)

Publisher
Inderscience Publishers
Copyright
Copyright © Inderscience Enterprises Ltd. All rights reserved
ISSN
1748-0698
eISSN
1748-0701
DOI
10.1504/IJSISE.2014.060056
Publisher site
See Article on Publisher Site

Abstract

Human face detection is the first step towards face recognition, video surveillance and bioinformatics applications. The first step in faces detection is skin colour detection. Skincolour detection in visible spectrum is a very challenging task as the skin colour in an image is sensitive to various factors such as sensor characteristics, illumination, optics and ethnicity. Many researchers emphasise that there is a relationship between surface colours and illumination which is closely related problem of colour constancy. Colour correction stage should come first before applying skin colour detection to get better recognition rate. In this paper, a new approach Illumination Reflection Problem (IRP) has been proposed to correct the skin colour in the image that suffers from illumination reflection problem. IRP approach succeeded to correct the colour of 95% of affected pixels from illumination reflection problem. Also, a new approach to solve colour constancy problem is proposed named MMCrCb (Mean of Medians of Cr Cb). The purpose of this correction approach is to prepare the image prior to applying skin detection technique. Its methodology based on transforming the image to YCbCr then correcting the values of Y, Cb and Cr. After doing correction, transform the image back to RGB. Images from Caltech Image Database that suffer from colour constancy problem were used to test the MMCrCb approach. Also nine skin colour detection techniques were investigated and compared with a new proposed technique for skin detection using HSL and R colour components. The data base used for testing that approach was the MUCT database. The MUCT database provides more diversity of lighting, age and ethnicity. The testing results proved that the proposed skin detection technique using HSL and R is the best among techniques in the literature. In addition to that, the use of MMCrCb colour constancy correction approach with the proposed skin detection technique increases the skin colour pixels classification rate of unbalanced colour images by 20%.

Journal

International Journal of Signal and Imaging Systems Engineering – Inderscience Publishers

Published: Jan 1, 2014

There are no references for this article.