Neighborhood linear discriminant analysis

作者：

Highlights：

• The neighborhood linear discriminant analysis (nLDA) is proposed to address multimodality in LDA.

• In nLDA, the scatters are defined on a neighborhood consisting of reverse nearest neighbors.

• The within- and between-neighborhood scatters can avoid estimating the subclasses in multimodal class.

• The nLDA performs significantly better than some existing discriminators, such as LDA, LFDA, ccLDA, LM-NNDA and l2,1-RLDA.

摘要

•The neighborhood linear discriminant analysis (nLDA) is proposed to address multimodality in LDA.•In nLDA, the scatters are defined on a neighborhood consisting of reverse nearest neighbors.•The within- and between-neighborhood scatters can avoid estimating the subclasses in multimodal class.•The nLDA performs significantly better than some existing discriminators, such as LDA, LFDA, ccLDA, LM-NNDA and l2,1-RLDA.

论文关键词：Linear discriminant analysis,Reverse nearest neighbors,Neighborhood linear discriminant analysis,Multimodal class

论文评审过程：Received 18 March 2020, Revised 2 November 2021, Accepted 4 November 2021, Available online 6 November 2021, Version of Record 13 November 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108422