基于粒子群寻优机制的图像分割方法

利用粒子群优化（eso）算法全局寻优、快速收敛的特点，结合模糊C-均值（FCM）图像分割算法提出一种新算法，用PSO算法代替了FCM算法的基于梯度下降的迭代过程，使算法具有很强的全局搜索能力，很大程度上避免了FCM算法易陷入局部极小的缺陷；同时也降低了FCM算法对初始值的敏感度。实验结果表明，与FCM相比该算法聚类更准确，效率更高，具有较高的分割速度和良好的抑制噪声的能力。

Image Segmenting Method Based on PSO Algorithm

A new method is proposed to combine Particle Swarm Optimization （PSO） algorithm which characterizes of global optimizing and higher convergence rate with Fuzzy C-means （FCM） image segmenting algorithm. PSO is used to replace the iteration process based on gradient descent of FCM, which enables a strong global searching capability and largely avoids the local minimum problem of FCM as well as reduces the sensibility of FCM to initial values. The experimental results show that the proposed method is more accurate and efficient than FCM with a better quality in segmenting and suppressing noises.