A comparison of pixel, edge and wavelet features for face detection using a semi-naive Bayesian classifier

Henry Schneiderman at Carnegie Mellon University developed a face detection algorithm based upon a semi-naive Bayesian classifier and 513 linear phase wavelets. This paper explores the relative value of these wavelet features compared to simpler pixel and edge features.. Experiments suggest edge features are superior for highly controlled lighting, while pixel features are better and more stable for uncontrolled lighting. Tests use the Notre Dame face data collected in Fall 2003 and Spring 2004 and use over 400, 000 face and non-face test image chips.