Image processing algorithms for Touch-Position estimation of an image-based areal touch sensor

In this paper, we propose an algorithm to estimate the touch position using an image-based areal touch sensor (IATS) that can soft physical contact. First, the principle of the proposed algorithm about touch position estimation is described. Then, the structure of the IATS for verifying this algorithm was described. Second, three experiments were processed to verify this algorithm. Then, the experimental data were obtained and analyzed. The error value was found to be 3.4 to 9.6 pixels as a result of comparison between the actual touch position coordinates and the algorithm-based touch position estimation coordinates. In addition, in the process of the estimation, the vibration phenomenon of the estimated touch position was detected. In order to minimize the vibration, Kalman filter was utilized. As a result, a standard deviation about error value of the touch position estimation coordinates before applying Kalman filter was 3.28 and after applying Kalman filter was 1.64.