Spatial moment sub-pixel edge locator based on cubic Bézier curve

Edge location of sub-pixel accuracy is an important technology for image processing. A novel approach to edge location of sub-pixel accuracy is proposed in this paper, which uses a cubic Bezier curve model to fit edges occurred in a digital image and overcomes the drawbacks of the models of line and parabola when there is an inflection point on the edge. The Levenberg-Marquardt iterative method is utilized to get the control points of the cubic Bezier curve. Experimental results illustrate the performance of the algorithm. These results show that the localization of the edges is much more accurate than that of the existing approaches when the shape of the fitted edge likes an unsymmetrical quadratic curve or a cubic one with an inflection point on it.