Ming CHEN, Feng ZHANG^*, Zhenhong DU, and Renyi LIU

Zhejiang Provincial Key Laboratory of GIS, Xixi Campus, Zhejiang University, Hangzhou 310007, China

(Received June 28, 2013; Accepted August 31, 2013)

Circle detection is significant in image processing and pattern recognition. We present a new algorithm for detecting circles, which is based on the global geometric symmetry of circles. First, the horizontal and vertical midpoint histograms of the edge image are obtained by using scan lines. Then, we apply the peak-finding algorithm to the midpoint histograms to look for the center of the circle. The normalized radius histogram is finally used to verify the existence of the circle and extract its radius. Synthetic images with different levels of pepper noise and real images containing several circles have been taken to test the performance. Experimental results demonstrate that the proposed algorithm has the advantage of computational efficiency as compared with the randomized Hough transform and some other algorithms.

Key words: circle detection, scan line, histogram, geometric symmetry

^*E-mail address: zhangfeng.zju@gmail.com