Finding initial estimates of human face location
KC Yow, Roberto Cipolla · Cambridge University Engineering Department Publications Database · 1995
This paper describes a method to find initial estimates of human face location in an image where the orientation and viewpoint of the faces are not known. Features such as eyes, nose and mouth are detected from the image using quadrature phase filters and grouped into potential face candidates. Affine invariants are used in grouping to overcome the problem of variation in viewpoint. An efficient searching algorithm is proposed to group these features based on the constraints in the geometry. A belief network is then constructed for each possible face candidate and the belief values updated by evidences propagating through the network. Different instances of detected faces are then compared using their belief values and improbable face candidates discarded. The algorithm is tested on different instances of faces with varying sizes, orientation and viewpoint and the results indicate a 93% success rate in detection under viewpoint variation. 1 Introduction Recognizing a human face in a s...