Fast circle detection algorithm based on sampling from difference area

Abstract The detection of circular targets is a basic problem in computer vision, especially in pattern recognition. Due to the low effective sampling rate, circle detection methods based on random sampling (like randomized Hough transform and randomized circle detection algorithm) result in heavy computation load and slow detection speed. Targeted at this problem, this paper proposes a fast circle detection algorithm based on the difference area sampling. When a candidate circle is determined to be a false circle, a number of samples are taken from its difference area if the number of points on the candidate circle reaches a certain number. And the sampling efficiency in the difference area is significantly higher than that of the random sampling, thus increasing the speed of the circle detection. A large number of experimental results also validate this advantage. The proposed algorithm has the same detection accuracy and robustness as the original algorithm, and the proposed method of sampling from the difference area boasts great potential in practical application as it can be directly applied to randomized Hough transform, randomized circle detection algorithm and their improved versions.

[1]  Zhanfeng Shen,et al.  A local voting and refinement method for circle detection , 2014 .

[2]  Erik Valdemar Cuevas Jiménez,et al.  Multi-circle detection on images inspired by collective animal behavior , 2012, Applied Intelligence.

[3]  Ali Özgün Ok,et al.  A New Approach for the Extraction of Aboveground Circular Structures From Near-Nadir VHR Satellite Imagery , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Lei Xu,et al.  A unified perspective and new results on RHT computing, mixture based learning, and multi-learner based problem solving , 2007, Pattern Recognit..

[5]  Kuo-Liang Chung,et al.  Efficient sampling strategy and refinement strategy for randomized circle detection , 2012, Pattern Recognit..

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

[7]  Magnus Andersson,et al.  A fast and robust circle detection method using isosceles triangles sampling , 2016, Pattern Recognit..

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

[9]  Emre Baseski,et al.  Circular Oil Tank Detection From Panchromatic Satellite Images: A New Automated Approach , 2015, IEEE Geoscience and Remote Sensing Letters.

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

[11]  Cuneyt Akinlar,et al.  EDCircles: A real-time circle detector with a false detection control , 2013, Pattern Recognit..

[12]  Erik Valdemar Cuevas Jiménez,et al.  Automatic multiple circle detection based on artificial immune systems , 2012, Expert Syst. Appl..

[13]  Bidyut Baran Chaudhuri,et al.  A survey of Hough Transform , 2015, Pattern Recognit..

[14]  Guili Xu,et al.  An efficient curve detection algorithm , 2016 .

[15]  Dario Cazzato,et al.  Randomized circle detection with isophotes curvature analysis , 2015, Pattern Recognit..

[16]  Yanhui Guo,et al.  A novel Hough transform based on eliminating particle swarm optimization and its applications , 2008, Pattern Recognit..

[17]  Lianyuan Jiang,et al.  Efficient randomized Hough transform for circle detection using novel probability sampling and feature points , 2012 .

[18]  Lei Zhang,et al.  On-orbit real-time robust cooperative target identification in complex background , 2015 .

[19]  A. Oualid Djekoune,et al.  Incremental circle hough transform: An improved method for circle detection , 2017 .

[20]  Yeong Oh Han,et al.  A study on development of automation diagnosis of liquid based cytology , 2015 .

[21]  Kuo-Liang Chung,et al.  A Pruning-and-Voting Strategy to Speed up the Detection for Lines, Circles, and Ellipses , 2008, J. Inf. Sci. Eng..