Accelerometer-based hand gesture recognition system for interaction in digital TV

This paper presents the design and implementation of a system of accelerometer-based hand gesture recognition. This system will be embedded within a modern remote control to improve human-machine interaction in the context of digital TV of Argentina. As the recognition of hand gestures is a pattern classification problem, two techniques based on artificial neural networks are explored: multilayer perceptron and support vector machine. This is performed in order to compare results and select the tool that best fits the problem. Jointly, signal digital processing techniques are used for preprocessing and adapting of the input signals to pattern recognition models. A gestural vocabulary of 8 types of gestures was used, which was also used by other similar works in order to compare results. An appropriate trade-off between the classifier recognition precision and resource utilization of the hardware platform is required in order to implement the solution within an embedded system. The obtained results of precision and utilization of resources are excellent.