This paper proposes new features for recognizing telltale bulb in dashboard. Typical feature employed in model-based pattern recognition is polygonal approximation points of object. But recognition using these dominant points has many mismatching coun...
This paper proposes new features for recognizing telltale bulb in dashboard. Typical feature employed in model-based pattern recognition is polygonal approximation points of object. But recognition using these dominant points has many mismatching counts in small model such as telltale bulb. To reduce mismatching counts, proposed features are the circle distribution of object pixel and the ratio of distance from center to boundary in object. This paper also proposes new decision function using three features. In simulation result, we make a comparison mismatching counts between recognition using dominant points and new recognition algorithm using three features.