Finding human faces automatically in an image is a difficult yet important first step to a fully automatic face recognition system. This paper presents an example-based learning approach for locating unoccluded frontal views of human faces in complex scenes. The technique represents the space of human faces by means of a few view-based "face" and "non-face" pattern prototypes. At each image location, a 2-value distance measure is computed between the local image pattern and each prototype. A trained classifier determines, based on the set of distance measurements, whether a human face exists at the current image location. We show empirically that our distance metric is critical for the success of our system.
展开▼
