中文摘要：

根据所采集图像的离散性特点，提出了一种基于蚁群聚类的新型的多模板图像边缘融合方法。该算法综合了图像聚类的方法和模板边缘提取的方法，运用蚁群聚类的思想来提取图像的边缘特征，并进一步融合多种边缘提取模板来设置聚类的启发式引导函数和初始聚类中心，从而避免了传统蚁群算法聚类搜索时的盲目性。系列仿真实验验证了这一方法的可行性和有效性。

英文摘要：

In light of the discrete characteristics of digital images, a novel type of multiple-template image edge fusion method based on ant colony clustering is proposed in this paper. The method integrates the image clustering approach with the template edge extraction, extracts image edge features by using the concept of ant clustering, and then builds up multiple templates for image edge extraction to set the heuristic function for clustering and the initial cluster center, which can avoid the blind search in traditional ant colony clustering. A series of simulation experiments demonstrated the feasibility and effectiveness of the proposed method.