A novel automatic picture fuzzy clustering method based on particle swarm optimization and picture composite cardinality

作者：

Highlights：

• We presented a novel automatic picture fuzzy clustering method called AFC-PFS.

• It automatically determined the most suitable number of clusters for a dataset.

• Picture Composite Cardinality was used for best matching of the number of clusters.

• AFC-PFS created both the most suitable number of clusters and related solutions.

• It produced closest numbers of clusters to real ones.

摘要

•We presented a novel automatic picture fuzzy clustering method called AFC-PFS.•It automatically determined the most suitable number of clusters for a dataset.•Picture Composite Cardinality was used for best matching of the number of clusters.•AFC-PFS created both the most suitable number of clusters and related solutions.•It produced closest numbers of clusters to real ones.

论文关键词：Picture fuzzy clustering,Number of clusters,Particle swarm optimization,Picture composite cardinality,Picture fuzzy sets

论文评审过程：Received 6 October 2015, Revised 15 June 2016, Available online 17 June 2016, Version of Record 3 September 2016.

论文官网地址：https://doi.org/10.1016/j.knosys.2016.06.023