The reviewed record of science sign in
Pith

arxiv: 1406.0023 · v1 · pith:WIIDGED4 · submitted 2014-05-30 · cs.CV

Circle detection using electro-magnetism optimization

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:WIIDGED4record.jsonopen to challenge →

classification cs.CV
keywords circlealgorithmdetectionoptimizationcandidatescirclesfunctionimage
0
0 comments X
read the original abstract

This paper describes a circle detection method based on Electromagnetism-Like Optimization (EMO). Circle detection has received considerable attention over the last years thanks to its relevance for many computer vision tasks. EMO is a heuristic method for solving complex optimization problems inspired in electromagnetism principles. This algorithm searches a solution based in the attraction and repulsion among prototype candidates. In this paper the detection process is considered to be similar to an optimization problem, the algorithm uses the combination of three edge points (x, y, r) as parameters to determine circles candidates in the scene. An objective function determines if such circle candidates are actually present in the image. The EMO algorithm is used to find the circle candidate that is better related with the real circle present in the image according to the objective function. The final algorithm is a fast circle detector that locates circles with sub-pixel accuracy even considering complicated conditions and noisy images.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.