Connectivity-based error evaluation for ellipse fitting
Tomonari Masuzaki, Yasuyuki Sugaya · 2015
We propose a new method for fitting an ellipse to a point sequence extracted from an image. This method can fit an ellipse if a point sequence consists of elliptic arcs and non-elliptic arcs such as line segments. Assuming that input points are spatially connected, we iteratively select inlier points and fit an ellipse to them by computing curvatures of the residual graph. By using simulated data and real images, we compare the performance of our method with existing methods and show that the accuracy and computation time of the proposed method is superior to existing methods.