Significantly Fast and Robust Fuzzy C-MeansClustering Algorithm Based on MorphologicalReconstruction and Membership Filtering
As fuzzy c-means clustering (FCM) algorithm issensitive to noise, local spatial information is often introducedto an objective function to improve the robustness of the FCMalgorithm for image segmentation. However, the introduction oflocal spatial information often leads to a high computationalcomplexity, arising out of an iterative calculation of the distancebetween pixels within local spatial neighbors and clusteringcenters. To address this issue, an improved FCM algorithmbased on morphological reconstruction and membership filtering(FRFCM) that is significantly faster and more robust than FCM,is proposed in this paper. Firstly, the local spatial informationof images is incorporated into FRFCM by introducing mor-phological reconstruction operation to guarantee noise-immunityand image detail-preservation. Secondly, the modification ofmembership partition, based on the distance between pixelswithin local spatial neighbors and clustering centers, is replacedby local membership filtering that depends only on the spatialneighbors of membership partition. Compared to state-of-the-art algorithms, the proposed FRFCM algorithm is simpler andsignificantly faster, since it is unnecessary to compute the distancebetween pixels within local spatial neighbors and clusteringcenters. In addition, it is efficient for noisy image segmentationbecause membership filtering are able to improve membershippartition matrix efficiently. Experiments performed on syntheticand real-world images demonstrate that the proposed algorithmnot only achieves better results, but also requires less time thanstate-of-the-art algorithms for image segmentation.
PDF
