A mean shift based fuzzy c-means algorithm for image segmentation

Image segmentation is an important task in many medical applications. One family of segmentation algorithms is based on the idea of clustering pixels with similar characteristics. C-means based approaches, in particular fuzzy c-means has been shown to work well for clustering based segmentation, however due to the iterative nature are also computationally complex. In this paper we introduce a new mean shift based fuzzy c-means algorithm that we show to be faster than previous techniques while providing good segmentation performance. The proposed clustering method incorporates a mean field term within the standard fuzzy c-means objective function. Since mean shift can quickly and reliably find cluster centres, the entire strategy is capable of optimally segmenting clusters within an image.