Kernel Bilateral Fuzzy C-means Clustering with Spatial Information for Image Segmentation
Download as PDF
Fuzzy clustering has widely been applied to pattern recognition, which emerged as an interesting alternative in image segmentation. However, fuzzy clustering lies in its inability to preserve edges and suppress noise, often leading to unsatisfactory segmentations. To solve this problem, a modified algorithm is derived by using bilateral filter. The first key concept of our method is its nonlinear filtering process, which exploits edge-preserving smoothing property to preserve the edge structures while weakening noise in segmentation. The second is that this technique takes into account the image spatial information term into the objective function, which are obtained by the mean output of bilateral filtering. The main advantages of the proposed approach are that it exhibits robustness to edge-preserving and noise and it is straightforward to implement in a simple way. Experimental results on both synthetic and real images demonstrate the effectiveness of the proposed method.
Fuzzy C-Means, Kernelized Fuzzy C-Means, Bilateral Filter, Spatial Information, Image Segmentation