基于蚁群及空间邻域信息的FCM图像分割方法-《郑州大学学报(工学版)》

文章信息/Info

Title:: Image segmentation based on the ant colony and improved FCM clustering algorithm with spatial information

Keywords:: Ant colony optimization algorithms; Watershed; Spatial constraints; Image segmentation

摘要:: 针对模糊C均值(FCM)聚类算法聚类个数难以确定、搜索过程易陷入局部最优的缺陷,把蚁群算法与改进的FCM聚类算法相结合,提出了一种基于蚁群算法的带有空间邻域信息的模糊C均值聚类图像分割算法.首先利用分水岭算法对图像进行初始分割,然后利用蚁群算法寻优,求得聚类中心和聚类个数,将其作为模糊C均值聚类的初始聚类中心和聚类个数进行模糊聚类.实验结果表明:由于聚类样本数量显著减少,很大程度上提高了聚类速度和抗噪能力,增强了算法的鲁棒性.

Abstract:: Because the number of fuzzy c-means (FCM) clustering algorithm is difficult to determine and the searching process is easy to fall into local optimum, the ant colony algorithm is combined with the improved FCM clustering algorithm, an image segmentation algorithm based on ant colony algorithm and fuzzy C-means clustering with spatial neighborhood information is proposed. Firstly, the watershed algorithm is used to segment the image initially, and then the ant colony algorithm is used to find the cluster center and the number of clusters, it is used as the initial cluster center and the number of clusters for fuzzy c-means clustering. The experimental results show that the clustering speed and the ability of anti-noise are greatly improved and the robustness of the algorithm is enhanced due to the significant reduction of the number of clustering samples.