الفهرس 
AbstractOnly 14 pages are availabe for public view
 |  | from | 103 |  |  |
| | | from | 103 | | |
Abstract
Human face detection is the first and most important step of face
analysis. But face detection is a difficult task in image analysis which has each
day more and more applications. Automatic human face detection from images
in surveillance and biometric applications is a challenging task due to the
variances in Image background, view, illumination, articulation, and facial
expression.
The existing methods for face detection can be divided into image based
methods and feature based methods. We have used an intermediate system, it is
image based in the sense that it uses a learning algorithm to train the classifier
with some well chosen train positive and negative examples. On the other hand,
it is also feature based because the features chosen by the learning algorithm are
lots of them directly related to the particular features of faces (eyes positions,
contrast of the nose bridge).
The main idea in building the detector is a learning algorithm based on
boosting called AdaBoost algorithm. AdaBoost is an aggressive learning
algorithm which produces a strong classifier by choosing visual features in a
family of simple classifiers and combining them linearly. The family of simple
classifiers contains simple rectangular wavelets which are reminiscent of the
Haar basis. A new image representation called Integral Image allows a very.