作者: Sven Kratz , Michael Rohs
关键词: Computer science 、 Trigonometry 、 Training set 、 Input device 、 Rapid prototyping 、 Speech recognition 、 Computer vision 、 Artificial intelligence 、 Gesture 、 User interface 、 Classifier (UML) 、 Gesture recognition
摘要: We present the $3 Gesture Recognizer, a simple but robust gesture recognition system for input devices featuring 3D acceleration sensors. The algorithm is designed to be implemented quickly in prototyping environments, intended device-independent and does not require any special toolkits or frameworks. It relies solely on trigonometric geometric calculations. A user evaluation of our resulted correct rate 80%, when using set 10 unique gestures classification. Our method requires significantly less training data than other recognizers thus suited deployed deliver results rapidly.