A threshold decision method of the object image by usingthe smart tag and the vision

摘要

We proposed a novel method for object recognition using the Smart tag system in the previous research. We identified the object easily, but could not assure the object pose, because the threshold problem was not solved. So we propose a new method to solve this threshold problem. Thismethod uses a smart tag to decide the threshold by recording color information of the image when the object feature is extracted. This method records the original of the object color information at the smart tag first. And then it records the object image information, the circumstance image informationand the sensors information continuously when the object feature is extracted through the experiments. Finally, it estimates the current threshold by recorded information. This method can be applied the threshold to each objects. And it can solve the difficult threshold decision problem easily.To approve the possibility of our method, we implemented our approach by using easy and simple techniques as possible.