Face recognition is a biometric identification method which in comparison with other methods such as finger print identification, speech, signature, hand written and iris recognition is shown to be more important both theoretically and practically. In principle, the biometric identification methods include a wide range of fields such as machine vision, image processing, pattern recognition and neural network. It has various applications such as in film processing, control access networks etc. During recent years the automatic recognition of a human face has become an important problem in pattern recognition. The reason is that structural similarity of human faces on one side and great impact of illumination conditions, facial expression and face orientation on the other side have made face recognition one of the most challenging problems in pattern recognition. In this thesis the advantages of face recognition system comparing to other biometric systems is mentioned. Several important algorithms of face recognition are reviewed and the appearance based methods are introduced which can be categorized into linear and nonlinear methods. Also some methods are introduced for increasing the recognition rate such as CCA and KPCA. Distance based and RBF neural network ltr"