<p>Advances in computer vision and machine learning have continually driven the evolution of image processing technologies, providing opportunities to enhance our ability to analyze and interpret digital images. This paper presents a specialized approach named <i>“Edge Detection of Mammography using improved Artificial Bee Colony” (edmABC)</i>, for edge detection and analysis of mammography images for the detection of breast cancer inspired by the foraging behavior of honeybees. This study has harnessed the Artificial Bee Colony (ABC) algorithm to identify and emphasize boundaries within mammography images. The primary goal is to enhance image edge detection of mammography images, which is crucial in facilitating clinical analysis and subsequent diagnosis by healthcare professionals. The proposed approach combines local search, information sharing, and exploration–exploitation of the ABC algorithm to identify potential edge points based on fitness values and improve edge accuracy. For this aim, this study has introduced opposition-based learning and chaotic systems into the population initialization stage, extracted grayscale values, and applied statistical estimation to further improve the final solutions of the proposed algorithm. The findings demonstrate that the <i>edmABC</i> method outperforms several standard edge detection techniques such as <i>Canny</i>, <i>Prewitt</i>, and <i>Sobel</i>. Combining the ABC algorithm alongside grayscale values and statistical estimation has impacted the results significantly. Therefore, this study positions <i>edmABC</i> as a promising solution for enhancing mammography image analysis.</p>