Hybrid gesture classifying method using K-NN and DTW for smart remote control

In this paper, we propose a hybrid gesture classifying method using K-NN and DTW based on electric field disturbance for gesture recognition for smart devices. Input patterns of Electric Potential Integrated Circuit (EPIC) sensors are projected into two dimensional movements in proposed preconditioning process. Change of surrounding electronic field caused by moving hands has been observed mainly around band of 10Hz. Butterworth IIR filter and Kalman filter are used to minimize the signal noises. Our proposed recognition process using K-NN with PCA and DTW can successfully identify ten different gestures with about 92% correct classification rate.