Fast and Efficient Circle Detection Schemes for Digital Image

The paper proposes two novel and efficient methods of circle detection from gray scale images. As a tool, we have used in one scheme ant colony algorithm. In other scheme, we have used ant regeneration and recombination system (ARRS), an entirely new approach developed by ourselves. In both the schemes presented here, three common steps were followed. Firstly, MATLAB edge detection operator converts a gray scale image into a binary one. Our schemes are then applied on this binary image to detect closed loops. Finally, these closed loops are tested for circle. The prime feature of the schemes is they can detect both intersecting as well as non intersecting circle from images consisting of different shapes. The first scheme is a modified application of traditional ant system algorithm in which accuracy in result is paid in terms of computing time. We, therefore, construct a new ant system ARRS which can detect circles with incredible time and memory efficiencies that make it useful in real time applications.