Effectively clustering by finding density backbone based-on kNN

作者：

Highlights：

• CLUB can easily find clusters with various densities, shapes and sizes.

• A new density computing method is presented.

• A novel cluster backbones identification method is proposed.

• Comprehensive experiments are performed to verify the performance of CLUB.

摘要

Highlights•CLUB can easily find clusters with various densities, shapes and sizes.•A new density computing method is presented.•A novel cluster backbones identification method is proposed.•Comprehensive experiments are performed to verify the performance of CLUB.

论文关键词：Clustering algorithm,Density backbone,k nearest neighbours

论文评审过程：Received 15 June 2015, Revised 24 March 2016, Accepted 25 April 2016, Available online 24 May 2016, Version of Record 22 June 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.04.018