應用模糊聚類與粒子演算法之色彩分群研究

Fuzzy clustering and particle swarm optimization applied to color clustering algorithm

游健忠(Chien-Chung Yu)

指導教授 ： 賀嘉律

國立中央大學/資訊電機學院/通訊工程研究所碩士在職專班/碩士(2011年)

摘要

目前在影像處理的領域中，圖像分割算是重要的一項影像處理。圖像分割可以透過色彩分群的方法達到圖像分割的目的。而透過圖像分割可以讓我們容易得到我們需要的部分，並將分離出來的部分加以處理。
模糊聚類演算法是屬於聚類演算法的一種，它是由K-Means改良而來的，它主要加上了模糊理論的概念，使得每一點的輸入向量以歸屬的程度來表現。但模糊聚類演算法本身有一些缺點，初始值的選擇會影像它分群的效果。所以我們利用群體智能粒子群優化演算法來找尋初始值，讓模糊聚類演算法來達到好的色彩分群效果。
所以我們本論文將結合模糊聚類演算法、粒子群演算法這二種來做為色彩分群，讓粒子群演算法做為初始值的搜尋的方法來改善模糊聚類演算法的收斂速度、分割的品質。

關鍵字

聚類演算法 ； 粒子群演算法 ； 群體智能 ； 色彩分群 ； 圖像分割

並列摘要

Nowadays, image segmentation is an important technique in the image processing sector. We can easily extract the necessary parts from the entire image through this technique.
Fuzzy C Means is a clustering algorithm coming from K-Means algorithm. The concept of fuzzy logic are applied to this method in which the performance on each point of the input vector has a degree of the belonging. The weakness of Fuzzy C Means is on the clustering effects when selecting the initial value of image. To achieve the good effect on image segmentation by using the Fuzzy C Means’ algorithm, we generate a method of intelligence particle swarm optimization algorithm to find the initial value.
We used two algorithm methods in image segmentation technique which are Fuzzy C Means and particle swarm optimization algorithm. Both improved the convergence’s speed and the segmentation’s quality of Fuzzy C Means.

並列關鍵字

Image segmentation ； Fuzzy C Means ； Swarm Intelligence ； PSO ； Particle Swarm Optimization ； Clustering Algorithms

參考文獻

[1] Selim, S. Z. And Ismail, M. A., K-Means type algorithms: A generalized convergence theorem and characterization of local optimality. IEEE Trans. Pattern Anal. Mach. Intell. 1984, 81–87.

[2] Zhang D Q，Chen S C．Kernel-based fuzzy clustering incorporating spatial constraints for image segmentation Proceedings of the Second International Conference on Machine Learning and Cyber-netics, Xi’an, 2003.

[3] Chuang K S，Tzeng H L, Fuzzy C-Means Clustering with spatial information for image segmentation[J], Comput. Med lmag. Graphics, 2006.

[5] Shi, Y. H., Eberhart, R. C., Parameter Selection in Particle Swarm Optimization, The 7th Annual Conference on Evolutionary programming, San Diego, CA., 1998.

[7] Kennedy J. The particle swarm: Social adaptation of know ledge . Proc IEEE Int Conf on Evolutionary Computation , 1997, pp.303-308.