A human face provides a variety of different communicative
functions, such as identification, perception of emotional expressions,
and lip-reading. Face perception is currently an
active research area in the computer vision community.
Much research has been directed towards feature recognition
in human faces. Three basic techniques are commonly used
for dealing with feature variations: correlation templates
[1][2], deformable templates [3], and spatial image invariants
[4]. Several systems of locating human face have been
reported. Eigenfaces, obtained by performing a principal
component analysis on a set of faces, are commonly used to
identify faces [5]. By moving a window covering a subimage
over the entire image, faces can be located within the entire
image. [6] reports a face detection system based on clustering
techniques. The system passes a small window over all
portions of the image, and determines whether a face exists
in each window. A similar system with better results has been
claimed by [7]. A different approach for locating and tracking
faces is described in [8]. This system locates faces by
searching for the skin-color. After locating a face, the system
extracts additional features to match this particular face. Recently,
Pfinder [9] uses skin-color to track human body.