ABSTRACT
Intelligent approaches for face detection and recognition utilize tools of artificial neural networks(ANNs) and machine learning techniques to detect and recognize faces. The development of an intelligent face recognition system requires providing sufficient information and meaningful data during machine learning of a face. However, the application of neural networks for face detection tasks is difficult and more challenging than face recognition, because of the difficulty in characterizing prototypical nonface images. Unlike face recognition, in which the classes to be discriminated are different faces, the two classes to be discriminated in face detection are images containing faces and images not containing faces. It is hard to get a representative sample of nonface images. In [110] the problem of using a huge training set for nonfaces is avoided by selectively adding images to the training set as training progresses. This bootstrap method reduces the size of the training set needed. The use of arbitration between multiple networks and heuristics to clean up the results significantly improves the accuracy of detection. A view-based approach to face detection [110] uses an artificial neural network to represent each view. Before going into the details of face detection using the neural network this chapter initially details the multilayer perceptron model of the artificial neural
network (ANN) and the backpropagation algorithm associated with neural network training.
