Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
The automated detection of humans in computer vision as well as the realistic rendering of people in computer graphics necessitates improved modeling of the human skin color. In this paper we describe the
 

Summary: 1
Abstract
The automated detection of humans in computer vision as well as the realistic rendering of people in
computer graphics necessitates improved modeling of the human skin color. In this paper we describe the
acquisition and modeling of skin reflectance data densely sampled over the entire visible spectrum. The data
collected through a spectrograph allows us to explain skin color (and its variations) and to discriminate
between human skin and dyes designed to mimic human skin color. We study the approximation of these
data using several sets of basis functions. Our study shows that skin reflectance data can best be approxi-
mated by a linear combination of Gaussians or their first derivatives. This result has a significant practical
impact on optical acquisition devices: the entire visible spectrum of skin reflectance can now be captured
with a few filters of optimally chosen central wavelengths and bandwidth.
1. Introduction
An accurate description of the color of human skin is key for both human detection/identification in computer vision
and for realistic rendering in computer graphics. Ideally, a good skin color descriptor should be physically accurate,
numerically advantageous and flexible in order to allow for skin tone variations.
The majority of existing skin color data is in the form of Red-Green-Blue (RGB) triplets. The prevalence of color
descriptors as a combination of these three color primaries can be partly attributed to the influence of the tristimulus human
visual perception mechanism. For most cases, describing color in the tristimulus space is sufficient for communicating
color information to a human observer. However, if the whole computation of light reflection and transfer is performed in
tristimulus space (see section 2), significant color distortions are introduced [6, 7]. Furthermore, the use of tristimulus rep-

  

Source: Angelopoulou, Elli - Department of Computer Science, Friedrich Alexander University Erlangen Nürnberg

 

Collections: Computer Technologies and Information Sciences