EDGE DETECTION USING BACTERIAL FORAGING AND UNIVERSAL LAW OF GRAVITY

Abstract

Edge detection is an important step used in various image processing algorithms. Edge gives the boundary of objects and provides information to separate the object from background or other overlapping objects. This work presents a new approach for edge detection inspired by Bacterial Foraging Algorithm (BFA) and Universal Law of Gravity. Among the many evolutionary algorithms proposed BFA is one of them. It consists of 4 stages viz chemotaxis, reproduction, swarming, elimination and dispersal. Chemotaxis stage decides the direction of movement of bacteria. Our aim is to move the bacteria through the edge pixels. The direction of movement of bacteria has been determined using the concept of Universal Law of gravity. The results of the proposed approach are compared with traditional edge detectors using different sample images. Quantitative analysis of the proposed approach with respect to traditional edge detectors has been done using Kappa and Entropy measures.