A Mobile Phone Gesture Recognition Approach Using Accelerometer Based on Dimension-Reduced HMM
An approach based on dimension-reduced HMM model is proposed in this paper to recognize the gesture commands in mobile games using accelerometer.In this approach,gesture recognition process consists of three phases: dimension reduction,HMM modeling,and gesture recognition.The performance of the proposed approach is evaluated using a dataset of eight types of gestures,and for each gesture 120 samples are collected from mobile accelerometer.The results demonstrate that the proposed method is effective to recognize different gestures by reaching an average accuracy of 96.25%.
HMM gesture recognition mobile accelerometer man-machine interaction dimension reduction feature Forward algorithm
Wei Song Wenwen Han Jian Ma Wendong Wang Kongqiao Wang
State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecomm Nokia Research Center,Beijing laboratory Beijing,China
国际会议
太原
英文
74-78
2011-02-26(万方平台首次上网日期,不代表论文的发表时间)