Image Segmentation using Hybrid Ant Colony Optimization: A Review

Nowadays segmentation is a promising research topic in image processing due to its applications in many fields like robotics, medical, remote sensing, facial recognition, satellite imaging, etc. Image segmentation is splitting an image into its constituent parts and is used to extract meaningful information. There is rapid and continuing progress in computerized image analysis particularly in medical image visualization. For accurate diagnoses of correct diseases using different modalities, image segmentation must be effective. Ant Colony Optimization (ACO) is a popular meta-heuristic method stimulated by the foraging behavior of ants. The indirect communication via chemical pheromone trails allows them to locate quick routes between their anthill and food sources. ACO is very robust and it can be easily combined with other methods to form hybrid optimization, yield better performance than the individual algorithms. So hybrid ACO is an effective algorithm for accurate segmentation. This paper presents some of the developed algorithms under this framework and gives an overview of how a hybrid ACO algorithm improves image segmentation performance.