A Gesture Recognition Method Based on Interval Distribution Probability

In view of the online real-time and the efficiency of the present methods of gesture recognition, this paper proposes a gesture recognition method based on interval probability probability. By using the infrared sensing technology to get the infrared reflection data of gestures, come pretreatment, establishes interval distribution probability feature templates according to their motion features. Finally, it makes a classification of the gestures and shows the output by using KNN. Via the experiments to identify 8 kinds of common gestures, the average recognition rate is up to 94.5%. As the experiments indicated, the system has the advantages of simple operation, low cost and can be used for a variety of intelligent interaction applications.