| Abstract: | In this paper, we present a circle/ellipse detection method based on genetic algorithms. Our genetic algorithm uses three edge points as the chromosome of candidate circles (x0, y0, r), and five edge points as the chromosome of candidate ellipses (x0, y0, e1, e2, theta). Fitness function evaluates if these candidate circles or ellipses are true. We present results of experiments with synthetic and real images demonstrating that the proposed method can detect the circles/ellpises effectively.
|