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.
By: Ying-Li Tian, Rudolf M. Bolle
Published in: RC22259 in 2002
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .