Automatic Neutral Face Detection Using Location and Shape Features
Ying-Li Tian, Rudolf M. Bolle
IBM Computer Science Research Report RC 22259, 2002.
This paper describes an automatic system to find neutral faces in images for facial expression analysis, face recognition and other applications. The system is based on an existing face detection and facial feature extraction system. Using these features, a window is placed in the detected region and normalized. In that fashion, zones in this window correspond to facial regions that are loosely invariant from subject to subject. Within these zones, shape features in the form of histograms and ellipses are extracted. These features, in addition to more global distance measures, are input to a classifier to arrive at a neutral/non-neutral decision. The system has achieved an average detection rate of 97.2%. Tests on an independent image database achieved an average classification rate of 95.3%, giving some indication of the robustness of the system.