الفهرس | Only 14 pages are availabe for public view |
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. |