A fast and robust ellipse detector based on top-down least-square fitting

Ellipse detection is a very important problem in the field of pattern recognition and computer vision. The existing algorithms often use a bottom-up strategy to combine edge points or elliptical arcs into ellipses, hence limit their robustness. In this paper, we propose a fast and robust ellipse detection algorithm which can accurately detect ellipses in the images. The main idea of the proposed algorithm is to exploit a novel top-down fitting strategy to combine edge points into ellipses and use integral chain to speed up the fitting process. Experimental results have demonstrated that our ellipse detection algorithm achieves a better performance than the state-of-the-art methods on the common evaluation measures of F1 score and average execution time.