Abstract: Recently, the most user-friendly systems in the biometric world are face recognition systems. In addition, they are one of the active research fields while the researchers work to ameliorate the effectiveness and competence of biometric implementations. The major challenge to be in these implementations is to extract the useful features sets which are not disturbed caused by number of factors, including person movement, illuminations, camera’s differences and other ecological and physical changes. Thus, AMM (Active Appearance Model) is one of the good population solutions which it can be used as a features extraction technique by accurate modeling under different physical and environmental situations. In this research, an AAM based face recognition system is proposed. Then, three different data sets YALEB, FERET and CASIA V5 which have been utilized for the first time in the evaluation. The experimental results showed that the performance of AAM is very powerful with face recognition.