New face segmentation technique insusceptible to illumination

This paper presents a robust face segmentation method dealing with the illumination problem effectively on color images. In color images, skin color is an important cue for face segmentation. Two sets of skin color data are acquired from Asian Database, i.e. normal conditioning skin pixels and illum...

Full description

Bibliographic Details
Main Authors: Lim, Hann, Ang, L., Seng, K.
Format: Conference Paper
Published: 2008
Online Access:http://hdl.handle.net/20.500.11937/46554
_version_ 1848757591552819200
author Lim, Hann
Ang, L.
Seng, K.
author_facet Lim, Hann
Ang, L.
Seng, K.
author_sort Lim, Hann
building Curtin Institutional Repository
collection Online Access
description This paper presents a robust face segmentation method dealing with the illumination problem effectively on color images. In color images, skin color is an important cue for face segmentation. Two sets of skin color data are acquired from Asian Database, i.e. normal conditioning skin pixels and illuminated skin pixels. Subsequently, both data are analyzed in YCbCr color space. As a result, proposed skin color normalization is implemented on the illuminated skin pixels with the intension of getting the skin pixel boundary as the priori knowledge. In order to remove the effect of illumination on images, Comprehensive Color Image Normalization, composing of row and column normalizations is applied on the input images. Row normalization is to reduce the lighting geometry while column normalization is to remove the color illumination. These normalized images are then compared to the predefined skin pixel boundary. Pixels that fall within the color boundary are denoted as skin color. In addition, elliptical skin boundary generates better performance than the rectangular boundary in the experiment. ©2008 IEEE.
first_indexed 2025-11-14T09:30:32Z
format Conference Paper
id curtin-20.500.11937-46554
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:30:32Z
publishDate 2008
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-465542017-09-13T13:39:37Z New face segmentation technique insusceptible to illumination Lim, Hann Ang, L. Seng, K. This paper presents a robust face segmentation method dealing with the illumination problem effectively on color images. In color images, skin color is an important cue for face segmentation. Two sets of skin color data are acquired from Asian Database, i.e. normal conditioning skin pixels and illuminated skin pixels. Subsequently, both data are analyzed in YCbCr color space. As a result, proposed skin color normalization is implemented on the illuminated skin pixels with the intension of getting the skin pixel boundary as the priori knowledge. In order to remove the effect of illumination on images, Comprehensive Color Image Normalization, composing of row and column normalizations is applied on the input images. Row normalization is to reduce the lighting geometry while column normalization is to remove the color illumination. These normalized images are then compared to the predefined skin pixel boundary. Pixels that fall within the color boundary are denoted as skin color. In addition, elliptical skin boundary generates better performance than the rectangular boundary in the experiment. ©2008 IEEE. 2008 Conference Paper http://hdl.handle.net/20.500.11937/46554 10.1109/ECTICON.2008.4600467 restricted
spellingShingle Lim, Hann
Ang, L.
Seng, K.
New face segmentation technique insusceptible to illumination
title New face segmentation technique insusceptible to illumination
title_full New face segmentation technique insusceptible to illumination
title_fullStr New face segmentation technique insusceptible to illumination
title_full_unstemmed New face segmentation technique insusceptible to illumination
title_short New face segmentation technique insusceptible to illumination
title_sort new face segmentation technique insusceptible to illumination
url http://hdl.handle.net/20.500.11937/46554