The goal of this project is to create neural network-based face detection system to identify people from a video sequence. A database containing the images of the people to be identified in the video sequence is created. Using the face detection code the faces inside the video sequence are cropped for recognition. It will eliminate background influence as much as possible. The face space is described by a set of feature vectors obtained using the discrete cosine transform (DCT).This DCT feature vector is then fed into Artificial Neural Networks(ANN) which are used to recognize the faces through learning correct classification.

Key words: Artificial Neural Network,DCT, Back PropagationAlgorithm, Motion Detection, HeadTracking