Fuzzy clustering with spatial constraints for image thresholding

Image thresholding plays an important role in image segmentation. This paper presents a novel fuzzy clustering based image thresholding technique, which incorporates the spatial neighborhood information into the standard fuzzy c-means (FCM) clustering algorithm. The prior spatial constraint, which is defined as weight in this paper, is inspired by the k-nearest neighbor (k-NN) algorithm and is modified from two aspects in order to improve the performance of image thresholding. The algorithm is initialized by a fast FCM algorithm, in which the iteration is carried out with the statistical gray level histogram of image instead of the conventional whole data of image; therefore its convergence is fast. Extensive experiment results and both qualitative and quantitative comparative studies with several existing methods on the thresholding of some synthetic and real images illustrate the effectiveness and robustness of the proposed algorithm.