ON EXPERIMENTAL COMPARISON OF COLOR AND SUPERVISED FACE DETECTION

Viola-Jones  algorithm  and  skin  detection  are  the  two  widely  used  approaches  for  face detection.  This  paper  aims  at  showing,  experimentally,  the  trade-offs  associated  with each of the  algorithm. The  parameters  used  in  this  work  are  the  ones  encountered  in real images. These  include  the  illumination, color-space  representation,  face  orientation, image  sharpness  and  image  complexity. Experimentally, the peculiarities associated with each algorithm are shown. Based on these experimental results, the situations are commented upon where these algorithms will be efficacious. This paper moreover aims at to provide an objective comparison of the two algorithms rather than going into the subjective details of peculiarities of any individual implementation