Abstract
This paper is concerned with a new technique of curve fitting. The technique has various phases including extracting outlines of images, detecting corner points from the detected outline, addition of extra knot points if needed. The last phase makes a significant contribution by making the technique automated. It uses the idea of Stochastic Evolution to optimize the shape parameters in the description of the generalized cubic spline. It ultimately produces optimal results for the approximate vectorization of the digital contour obtained from the planar images.