Face recognition using neural networks

An approach to the problem of face recognition using a discrete cosine transform (DCT) and neural networks is presented. The DCT is used to extract features from the high dimensional facial data. Two different neural networks are used. The standard backpropagation neural network is used in a "network per person" implementation, while the counterpropagation network is used in a database implementation. On a database of 83 distinct subjects, with 5 learning views and 5 testing views per subject, a classification rate of 84% was achieved with the counterpropagation network, while a true positive classification rate of 77%, and a true negative classification rate of 97% was achieved with the backpropagation network.