Perpustakaan Digital ITB

Face detection is one of the most important preprocessing step in face recognition systems used in biometric identification. Face detection can also be used in searching and indexing still image or video containing faces in various size, position, and background. This paper describes a face detection system using multi ayer perceptron and Quickprop algorithm. The system achieves its ability by means of learning by examples. The training is performed using active learning method to minimize the amount of data used in training. Experimental results show that the accuracy of the system strongly depends on the quality and quantity of the data used in training.