Abstract:
Network access control using face recognuton
increases the user-friendliness in mobile phones
and human-computer interaction. In order to
realize a real time system implemented on
handheld devices with low computing power, low
complexity algorithms for face detection are
required. This paper introduces a fast algorithm
for face detection in video sequences, using a
skin color model in the HSV color space. These
algorithms are fast, robust and reliable and they
permit the segmentation and tracking of multiple
instances of faces in thumbnail images. The
method is designed and implemented to work
well with color images with varying lighting
conditions and inhomogeneous background. The
paper targets mobile handsets such as the
NOKIA 9500 Communicator.
