关键词: 端点, 蚁群, 高斯分布, 邻域差, 相似度

Abstract: The study presented an ant colony algorithm to implement edge linking. The proposed approach was based on original image and the edge image gained by traditional approaches to analyze the endpoints, and then set up pheromone values with Gaussian distribution around the endpoints in order to make the ants move to the endpoints faster. The visibility of the paths was determined by pixel similarity，neighboring difference and the direction of the edges synthetically, which made the ants move along the real edge pixels. The experimental results indicate that the proposed edge linking approach is efficient and good at compensating the broken edges.

Key words: endpoint, ant colony, Gaussian distribution, neighboring difference, similarity