Neuroscientists believe that human beings recognize faces not only by utilizing some holistic search among all learned faces, but also through a feature analysis that aimed to specify more important features of each specific face. In this paper, we propose a hierarchical classifier that uses both holistic search and per face dominant feature analysis to recognize faces. Reinforcement learning is used to find a set of dominant features for each image in a training dataset. Wavelet transform is employed as a preprocessing tool, which results in higher discrimination among classes. Simulation studies justify the better performance of the proposed method as compared to that of eigenface method.