This paper presents an approach to enhance edge detection in images using Ant Colony Optimization (ACO) algorithms, specifically the Ant Colony System (ACS). By transforming images into graph representations and leveraging the collective intelligence of virtual ants, the proposed method eliminates the need for complex mathematical functions and thresholding techniques. Strategies for initializing ants based on heuristic information and dynamically reinitializing ants based on performance are explored to improve efficiency and accuracy. Experimental results demonstrate the effectiveness of the approach in producing accurate edge maps while mitigating issues such as noise and loss of edge details. Future research directions include refining heuristic strategies and exploring hybridization techniques to further enhance edge detection performance.