Assessment the ants number and iteration in ant colony optimization for edge detection

• Main Authors: Jebur, Majid R., Hasan, Luma S.
• Format: Conference Proceeding
• Language: English
• Subjects: Algorithms; Ant colony optimization; Edge detection; Error analysis; Heuristic methods; Image processing; Iterative methods; Optimization; Parameters
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/5.0161470

One of the most important purposes of image processing is finding the information about objects in the image file especially detecting the boundary for an edge. Image edge detection is the critical step in image processing. This paper presents the Ant colony optimization (ACO) as a metaheuristic optimization algorithm that depends on the ant’s behavior in for searching food by detecting the edge in the image gray file by proposing a new formula for computing the count of ants by decreasing it with 10%, 30% and 50% of the square root of the multiplication between some rows with columns of the image file. it is performed on different images sizes (128x128, 256x256) with different values of parameters such as the number of ants, the number of iterations then examine the edge detection in the image file by computing the important parameters for solving any problem, especially the time complexity (elapsed time ) and mean square error (MSE) with PSNR. When analyzing the results of ACO to evaluate the best value of parameters that influenced the success of detecting the edge points, we deduced that when decreasing the number of iterations, the number of ants gives the best result for edge detection.