Joint enhanced low-rank constraint and kernel rank-order distance metric for low level vision processing

作者：

Highlights：

• Unsupervised low vision processing methods are proposed.

• Methods are based on enhanced low-rank constraint and similarity evaluation.

• Enhanced low-rank constraint mining basic information of nonlinear data with noise.

• Two similarity evaluation methods are designed to deal with high-level noise.

摘要

•Unsupervised low vision processing methods are proposed.•Methods are based on enhanced low-rank constraint and similarity evaluation.•Enhanced low-rank constraint mining basic information of nonlinear data with noise.•Two similarity evaluation methods are designed to deal with high-level noise.

论文关键词：Low-level vision,Low-rank constraint,Similarity,Clustering,Principle component analysis,Noise

论文评审过程：Received 5 November 2021, Revised 21 January 2022, Accepted 22 March 2022, Available online 2 April 2022, Version of Record 14 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116976