At present, the model of computer machine is something that is placed at the corner of the room because it is deaf, dumb and blind as well as unaware of the surrounding environment. The most interactive entity with computers is human beings. Imagine a machine that can detect the presence of human being by detecting human face and follows it during the interaction process (tracking). The demand to implement this scenario is to come up with a technique that responds in real time and able to detect the face under varying scale, translation and rotation transformation with facial feature localized. This book discusses in detail the real time implementation of face detection/tracking, face/non-face classification and facial feature localization in video sequence that is invariant to scale, translation, and rotation transformation.