A new clustering method based on morphological operations

作者：

Highlights：

• We propose a new clustering method based on the morphological operations.

• We transform the dataset into the image space and connect the neighboring points by morphological dilation.

• The connected domains with different labels are generated by iterative morphological dilation.

• The points in the dataset are clustered based on their distances to the labeled connected domains.

摘要

•We propose a new clustering method based on the morphological operations.•We transform the dataset into the image space and connect the neighboring points by morphological dilation.•The connected domains with different labels are generated by iterative morphological dilation.•The points in the dataset are clustered based on their distances to the labeled connected domains.

论文关键词：Clustering,Morphological operations,Dilation,Label

论文评审过程：Received 5 September 2019, Revised 10 November 2019, Accepted 25 November 2019, Available online 26 November 2019, Version of Record 2 December 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.113102