Hand Gesture Recognition Based on Decision Tree

In this paper, we present a new technique for the recognition of hand gesture using decision tree method based on information entropy. Some rules are derived from the decision tree using training data, which can classify sixty-five different hand gestures. Normalization for all sensors in a DataGlove are also proposed to model the data variations of each sensor, which result from the same gesture variations. Compared with ANN, the proposed decision tree approach can not only improve the recognition performance by 12.2%, but also overcome the limitation of ANN in tedious training time. Hand gesture recognition is important for the communication between person with hearing ability and the hearing impaired as well as the research on the human-computer interface [1]. There are some approaches used in hand gesture recognition, such as ANN [2][3][4], HMM [5] and recursive induction [6]. The neural network algorithm for classification employs a method o