A dynamic programming approach for fitting digital planar curves with line segments and circular arcs

A curve-fitting method is proposed to approximate digital planar curves using line segments and circular arcs. Two subjective judgment criteria for perceptual significance are discussed. Then, an objective measure of perceptual error is defined based on the two criteria to evaluate the synthesized curve. For each sub-segment of the given digital curve, an optimal analytic curve can be designed to minimize the perceptual error of fitting. Using dynamic programming, we locate the optimal segmentation points which minimize the overall perceptual error. Experiments show that our method gives perceptually more significant representations of digital curves. (C) 2001 Elsevier Science B.V. All rights reserved.