On-Line, Alphabet-Independent, Gestural Recognition Using Probabilistic Properties

We present an approach to alphabet-independent gestural recognition which differs from existing techniques such as curve-matching in that it attempts to approximate the functionality of the feature-based approaches while allowing the advantages which result from alphabet independence. Our approach uses a probabilistic model to analyze an alphabet based on user supplied samples and to effectively describe the symbols as a collection of properties or attributes which are either absent or present in the particular symbol with a known probability. These properties are then used to test an unknown symbol and a simple cost function is used to determine the recognition result.