DocumentCode
419588
Title
Skin color detection using multiple cues
Author
Yang, Jinfeng ; Fu, Zhouyu ; Tan, Tieniu ; Hu, Weiming
Author_Institution
Inst. of Autom., Chinese Acad. of Sci., Beijing, China
Volume
1
fYear
2004
fDate
23-26 Aug. 2004
Firstpage
632
Abstract
In this paper, we present a novel space transformation to describe the skin and non-skin attributes, and build a new non-linear skin color classifier combining the spatial and probabilistic distributions of pixels. To weaken the illumination effect on images, we introduce a new gamma correction (GC) method. Experimental results show that our approach has good performance in skin color detection.
Keywords
curve fitting; image classification; image colour analysis; image segmentation; skin; curve fitting; gamma correction method; illumination effect; multiple cues; nonlinear skin color classifier; nonskin attributes; probabilistic pixel distribution; skin attributes; skin color detection; space transformation; spatial pixel distribution; Automation; Histograms; Humans; Laboratories; Lighting; Object recognition; Organizing; Pattern recognition; Skin; Table lookup;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on
ISSN
1051-4651
Print_ISBN
0-7695-2128-2
Type
conf
DOI
10.1109/ICPR.2004.1334237
Filename
1334237
Link To Document