Fast and robust image segmentation using an superpixel based FCM algorithm

Through semantically grouping pixels in local neighborhoods, superpixels can capture image redundancy and significantly improve the performance of post-processing algorithms. In this paper, we investigate the application of superpixels in FCM framework, and propose a modified FCM algorithm SPFCM which utilizes superpixels as clustering objects instead of pixels. Superpixel and its neighborhood increase the clustering granularity and allow us to compute the objective function on a naturally adaptive domain rather than on a fixed window, so our algorithm can make full use of the spatial information and is more robust to noise. Due to the compact image representation based on superpixels, the computational complexity of our method is also drastically reduced. Experimental results on both synthetic and real images demonstrate the effectiveness and efficiency of our algorithm.