Boundary segmentation by detection of corner, inflection and transition points

For future intelligent man-machine systems with vision, it is necessary to visualize the results of shape and motion and analysis of observed objects in the images. As for object recognition, there are at least three steps. The first is to detect edges which correspond to the boundaries of objects (edge detection). The second is to segment each boundary into simple fine or curve segments (image segmentation). The third is to match those features between the data and the model (feature extraction). The paper presents a new method for the second step: boundary segmentation. It can detect not only corners but inflection points on which the sign of the curvature changes and transitional points on which a line and a curve connect smoothly without any delicate threshold. It also calculates the curvature and the normal vector at each point on the boundary with good accuracy. The features extracted by the proposed method are useful for both machine vision and visualization.<>