Shoulder Point Detection: A Fast Geometric Data Fitting Algorithm

Abstract

In this paper we present a novel and efficient method, called shoulder point detection (SPD), for computing a planar rational quadratic Bézier curve to approximate a target shape defined by a set of dense and noisy data points. Our contribution is utilizing from one of the exclusive properties of Conic Splines, called the shoulder point(SP) for speed up of the curve fitting process. The SPD can be summarized in the following two steps: first, one data point of input data set is detected as a shoulder point through a heuristic approach. Then in step2, detected shoulder point is utilized to generate a quadratic rational Bézier curve as fitting result of data set. Splitting the input data points into the some segments and applying the proposed method locally can guarantee the accuracy of fitting process. We show that SPD is significantly faster than other data fitting methods used currently in the field of curve fitting since the fitting results are reasonably accurate.