Edge Detection Improvement by Ant Colony Optimization Compared to Traditional Methods on Brain MRI Image

An image is considered as a set of pixels that are connected in such a manner to form a boundary between two disjoints regions. Typically, the edge detection approach goes through the segmentation process by segmenting an image into regions of discontinuity. Hence it is a technique for marking sharp intensity changes. In this paper, it presents the Ant Colony Optimization based mechanism to compensate broken edges. There are various traditional edge detection techniques as Prewitt, Robert, Sobel, Marr Hildrith and Canny operators. On comparing them, it can be seen that Canny edge detector performs better than all other edge detectors on aspects such as it is adaptive in nature, generally performs better for noisy image by giving sharp images. Also it has been seen that remainders of pheromone trail as compensable edges are needed after finite iterations. Experimental results prove that compared to traditional image edge detection operators, the proposed Ant Colony Optimization(ACO) approach is very efficient in broken edges and more efficient than the traditional ones. The proposed ACO-based edge detection approach is to establish particularly a pheromone matrix that represents the edge information presented at each pixel of the image, according to the movements of a number of ants which are supposed to be dispatched in order to move on the image. General Terms Image Processing, Pattern Recognition, Multi-objective Optimization Algorithms