This book attempts to provide an automatic face recognition system based on the important facial features from multi-expression sequence face images. The designed system is based on feature-average based using back propagation neural networks. The system has separated into three major phases, feature extraction, averaging (approximation), and face recognition. The feature extraction phase has been implemented on assumption the location of the essential features of the face. The average phase has been implemented to reduce the diemensions of the features vectors by taking the average of the features from the multi expression faces. Finally tHe face recognition classification has been applied using back propagation neural networks. .