Robust face recognition is a challenging goal because of the gross similarity in shape and configuration of all human faces accompanied by the large differences between face images of the same person due to variations in lighting conditions, view points, head poses and facial expressions. This problem is further exacerbated when only one image is available per person for registration and matching. This book reviews the state of the art face recognition methods and analyzes challenging face variations in illuminance and expression. We also propose in this book a discriminative principal component analysis method that can simultaneously deal with these variations using only a single image per person. This approach is further extended by combining multile classifiers to enhance the borustness and discrimination.