Ellipse Detection by the RHT Based on Center Extraction

The useless samplings and accumulations of randomized Hough transform （RHT） are largely reduced with the help of the ellipse’s shape control point constraint and the constraint of normals at the endpoints of a chord.The false candidate ellipses introduced by the same distorted ellipse were eliminated effectively using the fuzzy confidence based on vision perceptual grouping.The experimental results show that compared with the other ellipse detection method based on RHT,our proposed method has the advantage of higher detection speed and accuracy as well as strong resistance to ellipse’s partial occlusion and deformation.