An artificial Ant based novel and efficient approach of regular geometric shape detection from digital image

Abstract

The paper presents a novel and efficient method of regular geometric shape detection from gray scale images. Artificial ant based methods have not been used much in the field of image processing. This paper demonstrates how artificial ants can be used effectively to extract regular geometric shapes from images. We propose here ant regeneration and recombination system (ARRS), an entirely new approach developed by ourselves. Our scheme of detection of shapes comprises of three steps. Firstly, MATLAB edge detection operator converts a gray scale image into a binary one. Ant regeneration and recombination system algorithm is then applied on this binary image to detect closed loops. Finally, these closed loops are tested for different geometric shapes like circle, ellipse, rectangle and square. The most important aspect of the scheme is it can detect both intersecting as well as non intersecting regular shapes from images consisting of different open and closed loop configurations. It is the incredible time and memory efficiency of the scheme that makes it useful in real time applications where decisions have to be taken within a very small time interval by observing an image.