Face recognition refers to the task of identifying a person in a given image. This is different from face detection where we locate the face in a given image. During face detection, we don't care who the person is; we just identify the region of the image that contains the face. Therefore, in a typical biometric face recognition system, we need to determine the location of the face before we can recognize it.
Face recognition is very easy for humans. We seem to do it effortlessly, and we do it all the time! How do we get a machine to do the same thing? We need to understand what parts of the face we can use to uniquely identify a person. Our brain has an internal structure that seems to respond to specific features, such as edges, corners, motion, and so on. The human visual cortex combines all these features into a single coherent inference. If we want our machine...
