Initial Performance Improvement for Fuzzy RANSAC Algorithm Based on Weighted Estimation Model

The computer vision involves many modeling problems with preventing noise caused by disturbance and sensing unit conditions. In order to improve computer vision system performance, a robust modeling technique must be developed for essential models in the system. The random sample consensus (RANSAC) and least median of squares (LMedS) algorithm have been widely applied in such issues. However, the performance deteriorates as the noise ratio increases and the modeling time for algorithms tends to increase in industrial applications. As an effective technique, we proposed a new fuzzy RANSAC method based on reinforcement learning concept for robust modeling. In this study, we proposed a new technique for the fuzzy RANSAC in order to improve learning performance in initial learning stage based on weighted modeling technique. Through modeling synthetic nonlinear data and camera homography experiments, the performance of the technique was evaluated. Their results found the proposed technique to be promising for improving modeling performance in initial learning stage.