Machine Recognition of Auslan Signs Using PowerGloves: Towards Large-Lexicon Recognition of Sign Language

Instrumented gloves use a variety of sensors to provide information about the user's hand. They can be used for recognition of gestures; especially well-deened gesture sets such as sign languages. However, recognising gestures is a diicult task, due to intrapersonal and inter-personal variations in performing them. One approach to solving this problem is to use machine learning. In this case, samples of 95 discrete Australian Sign Language (Auslan) signs were collected using a Power-Glove. Two machine learning techniques were applied { instance-based learning (IBL) and decision-tree learning { to the data after some simple features were extracted. Accuracy of approximately 80 per cent was achieved using IBL, despite the severe limitations of the glove.