Adaptive spatially weighted fuzzy c-means clustering for image segmentation

Fuzzy c-means (FCM) clustering algorithm is a popular algorithm in the field of image segmentation. In this paper, an adaptive spatially weighted FCM clustering (ASWFCM) is proposed, to improve the performance of image segmentation. Through defining the weight of each pixel neighborhood and incorporating the spatial weights into the traditional Fuzzy c-means objective function, the image information which related to local spatial is integrated into the segmentation approach. Because of those spatial weights of neighboring pixels are fully adapted to the local image content and can effectively detect the anisotropy of neighborhood, the proposed algorithm improves the robust to noise. Both synthetic and real image experimental results verify the accuracy and the robustness of the ASWFCM method.