Example-based Learning for View-based Human Face Detection

Finding human faces automatically in an image is a diicult yet important rst step to a fully automatic face recognition system. It is also an interesting academic problem because a successful face detection system can provide valuable insight on how one might approach other similar object and pattern detection problems. This paper presents an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based \face" and \non-face" prototype clusters. At each image location, a diierence feature vector is computed between the local image pattern and the distribution-based model. A trained classiier determines, based on the diierence feature vector, whether or not a human face exists at the current image location. We show empirically that the prototypes we choose for our distribution-based model, and the distance metric we adopt for computing diierence feature vectors, are both critical for the success of our system.