Primitive curve generation based on multiscale contour figure approximation

We propose a method to generate primitive curves from a set of given contour figures. The primitive curve is a partial shape which is commonly seen in given contours, and describes total characteristic shape of them. The proposed method, first, approximates every given contour figure by smoothing out only small details. The amount of smoothing is determined adoptively with the size of the details. In order to detect the details and their sizes, we use the scale-space analysis. Then, each approximated contour is split at corner points into curves. Each split curves describe partial shape of each given contour. Scale-space analysis helps to detect the global corner points. Next, we make clusters of those split curves based on the shape similarity. Finally, we generate primitive curves by obtaining average curves of each cluster.