节点文献
基于KFCM与SAPSO算法的图像分割
A novel method for image segmentation based on kernel fuzzy c-means and SAPSO algorithm
【摘要】 为了克服基于FCM算法的图像分割技术对噪声敏感和运算效率低等缺点,利用KFCM算法对于噪声的鲁棒性质,以及模糊退火算法Metropolis准则和粒子群算法相结合的智能全局搜索能力,改进了图像分割技术。实验表明:该算法具有一定的降噪和全局搜索能力,提高了运算速度及图像分割效果。该算法对于丰富图像分割研究具有一定的参考价值和指导意义。
【Abstract】 A new fuzzy algorithm based on SAPSO and KFCM is presented in this paper,which overcomes the shortcomings of the local optima and sensitivity to initialization from fuzzy C-means algorithm (FCM). The new algorithm takes advantage of the robustness of KFCM,the capacity of global search in PSO algorithm and the ability of jumping out of the local optima in SA to improve the FCM method. An experiental study demonstrates that the algorithm presented avoids the local optima and increases the convergence speed. The study is a valuable reference and of significance for image segmentation.
【Key words】 kernel; fuzzy c-means; simulated annealing; particle swarm optimization; image segmentation;
- 【文献出处】 辽宁工程技术大学学报(自然科学版) ,Journal of Liaoning Technical University(Natural Science) , 编辑部邮箱 ,2010年05期
- 【分类号】TP391.41
- 【被引频次】7
- 【下载频次】104