Litcius/Paper detail

Selection of Optimal Number of Clusters and Centroids for K-means and Fuzzy C-means Clustering: A Review

A Pugazhenthi, Lakshmi Sutha Kumar

20202020 5th International Conference on Computing, Communication and Security (ICCCS)25 citationsDOI

Abstract

In image segmentation, clustering is the process of sub dividing the whole image into the meaningful sub images. The most commonly used image segmentation algorithms such as K-means and Fuzzy c-means clustering face the specific important problem in selecting the optimal number of clusters and the corresponding cluster centroids. Plenty of research works have been done on the limitations of the said clustering algorithms to improve the efficient isolation of clusters. This paper enumerates the works done by different researchers in selecting the initial number of clusters and the centroids using K-means and Fuzzy c-means clustering. The limitations and applications of the above mentioned clustering algorithms are explored.

Topics & Concepts

Cluster analysisCentroidFuzzy clusteringComputer scienceArtificial intelligenceImage segmentationPattern recognition (psychology)FLAME clusteringData miningSelection (genetic algorithm)Correlation clusteringk-medians clusteringCURE data clustering algorithmFuzzy logicCluster (spacecraft)Single-linkage clusteringFace (sociological concept)SegmentationSociologySocial scienceProgramming languageAdvanced Clustering Algorithms ResearchImage Retrieval and Classification TechniquesRemote-Sensing Image Classification
Selection of Optimal Number of Clusters and Centroids for K-means and Fuzzy C-means Clustering: A Review | Litcius