Kinect-based mid-air handwritten digit recognition using multiple segments and scaled coding

Human-computer interaction has attracted much attention in recent years, especially in the field of entertainment. In our previous study, we presented an effective method of Kinect-based mid-air handwritten digit recognition for a potential application to TV remote controllers. However, its recognition accuracy is only about 86.7%. In this study, we propose an improved method, based on multiple segments and scaled coding. Experimental results show that the proposed method can elevate the accuracy up to 94.6%.