Classifying Variable Objects Using a Flexible Shape Model

Point Distribution Models (PDMs) are statistical mo dels which represent objects whose shape can vary. A useful feature of PDMs is their ability to capture the shape of variable objects within a training set with a small number of shape parameters. This compact and accurate parametrization can be used for the design of efficient classification systems. In this paper we de scribe a classification system which uses shape para meters. We have tested the system on classifying hand outlines, face outlines and hand gestures; experi mental results are presented.