22-08-2012, 03:36 PM
Human Skin Colour Clustering for Face Detection
Human Skin.pdf (Size: 1.72 MB / Downloads: 48)
Abstract
Computer vision is one out of many areas that wants to understand
the process of human functionality and copy that process with
intention to complement human life with intelligent machines. For better
human–computer interaction it is necessary for the machine to see people.
This can be achieved by employing face detection algorithms, like the one
used in the installation “15 Seconds of Fame”. Mentioned installation unites
the areas of modern art and technology. Its algorithm is based on skin
colour detection. One of the problems this and similar algorithms have to
deal with is sensitivity to the illumination conditions under which the input
image is captured. Hence illumination sensitivity influences face detection
results. One of the aspects from which we can observe illumination influence
is the choice of the proper colour space. Since some colour spaces
are designed to eliminate the influence of illumination (brightness) when
describing colour of an object, an idea of using such a colour space for
skin-colour detection has been taken under consideration and some of the
methods have been researched and tested.
INTRODUCTION
Installation “15 Seconds of Fame”
The installation “15 Seconds of Fame” [7] is an interactive
art installation, which intends to make instant celebrities out of
common people by putting their portraits on the museum wall.
The idea was inspired by the quotation of the famous artist Andy
Warhol: “In the future everybody will be famous for fifteen minutes”
and by the pop-art style of his work. The installation looks
like a valuable framed picture (Fig. 1). LCD monitor and digital
camera are built into the picture. Camera is connected to a computer,
which controls the camera and processes captured images.
Special software contains algorithm for face detection, which
looks for faces in captured images. Among them it chooses
one for further processing. In the next step a randomly chosen
portrait is processed with randomly chosen filter and random
colouring is applied afterwards. In such a way the portrait in a
pop-art fashion arises, which is afterwards shown on screen for
15 seconds.
2D COLOUR SPACE SKIN CLUSTERING METHODS
The skin cluster model is realized in YUV (Y CbCr) colour
space [3]. The realization is done in two different ways. While
both of them classify the pixels by using only Cb and Cr components,
we can mark this color space as 2D (chromatic) colour
space.
In the first case we describe skin colours with cluster determined
by two central curves (the centers) Cb(Y ) and Cr(Y )
and by deviation curves (spread of the cluster) WCb (Y ) and
WCr (Y ). Here we can notice that all curves depend on Y
component, which represents the luminance.
CONCLUSION
From the presented results we could conclude that in the face
detection algorithms that detect faces based only on colour information,
it is better to use skin detection in the 3D colour
space. We cannot say that this is a general truth, but our face
detection scheme supports this statement, as the segmentation
and afterwards the face confirmation stages of the algorithm perform
better if the skin colour clustering is done in the 3D colour
space.