¹College of Mathematics & Computer Science, Mianyang Normal University, Sichuan Province, P.R.China
²School of Software Engineering, Pingdingshan University, Henan Province, P.R.China

---

Abstract—In the process of image segmentation, the classic Fuzzy C-Means (FCM) algorithm is time-consuming and depends heavily on initialization center. Based on Graphic Processing Unit (GPU), this paper proposes a novel FCM algorithm by improving the computational formulas of membership degree and the update criterion of cluster centers. Our algorithm can initialize cluster centers purposefully and further optimize them according to the analysis on the thread model of the graphic hardware. The compared experimental results with the classic FCM algorithm show that our algorithm has obvious superiority in improving image segmentation quality and efficiency.

Index Terms—Image Segmentation, Graphic Processing Unit, parallel computing, Fuzzy C-Means

[PDF]

Cite: Haiyang Li, Zhaofeng Yang, Hongzhou He, "An Improved Image Segmentation Algorithm Based on GPU Parallel Computing," Journal of Software vol. 9, no. 8, pp. 1985-1990, 2014.