Efficient Method for Rapidly Detecting Circles Based on Edge-Tracking

An efficient method for rapidly detecting circles using edge-tracking and evidence-collecting is presented. First, edge points are tracked to form series of edge chains. Then three points are randomly selected from each edge chain to obtain a possible circle. In the end, an evidence-collecting process is applied to determine whether the possible circle is a true one or not. During the evidence-collecting process, in order to raise the efficiency, only points locating in the area between the circumscribed square and the inscribed square of the possible circle are selected to judge if they lie on the possible circle. Comparison experiments with the RCD method for detecting circles have been made in two ways of detecting precision and speed. Experimental results obtained from a synthetic image and several real images demonstrate that the proposed method is efficient and practical.

[1]  Shiu Yin Yuen,et al.  Efficient technique for circle detection using hypothesis filtering and Hough transform , 1996 .

[2]  Jiun-Jian Liaw,et al.  An effective voting method for circle detection , 2005, Pattern Recognit. Lett..

[3]  Josef Kittler,et al.  A survey of the hough transform , 1988, Comput. Vis. Graph. Image Process..

[4]  Aggelos K. Katsaggelos,et al.  Robust circle detection using a weighted MSE estimator , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[5]  Erkki Oja,et al.  Randomized hough transform (rht) : Basic mech-anisms, algorithms, and computational complexities , 1993 .

[6]  George Loizou,et al.  Computer vision and pattern recognition , 2007, Int. J. Comput. Math..

[7]  Raúl Enrique Sánchez-Yáñez,et al.  Circle detection on images using genetic algorithms , 2006, Pattern Recognit. Lett..

[8]  Erkki Oja,et al.  A new curve detection method: Randomized Hough transform (RHT) , 1990, Pattern Recognit. Lett..

[9]  Kuo-Liang Chung,et al.  An Efficient Randomized Algorithm for Detecting Circles , 2001, Comput. Vis. Image Underst..

[10]  Erkki Oja,et al.  Randomized Hough Transform , 2009, Encyclopedia of Artificial Intelligence.

[11]  Peng-Yeng Yin,et al.  A new circle/ellipse detector using genetic algorithms , 1999, Pattern Recognit. Lett..