基于鱼群算法优化normalized cut的彩色图像分割方法

摘要

为了克服传统的谱聚类算法求解normalized cut彩色图像分割时,分割效果差、算法复杂度高的缺点,提出了一种基于鱼群算法优化normalized cut的彩色图像分割方法.先对图像进行模糊C-均值聚类预处理,然后用鱼群优化算法替代谱聚类算法求解Ncut的最小值,最后通过最优个体鱼得到分割结果.实验表明,该方法耗时少,且分割效果好.%Traditional spectral clustering algorithm minimizing normalized cut criterion has an inaccurate result and a high algorithm complexity in color image segmentation. In order to improve these disadvantages, this paper proposed a color image segmentation method based on normalized cut and fish swarm optimization algorithm. It firstly used fuzzy C-means dealing with color image, then employed fish swarm optimization algorithm instead of spectral clustering algorithm to minimize normalized cut, finally got segmentation result by the optimal individual fish. Experimental results show that the method achieves consumes less time, and achieves a precise segmentation result.