Low-rank double dictionary learning from corrupted data for robust image classification

作者：

Highlights：

• A novel low-rank double dictionary learning (LRD2L) approach is proposed for robust image classification.

• It integrates the low-rank matrix recovery technique with the class-specific and class-shared dictionary learning.

• It can effectively handle the image corruptions in both training and testing samples, which are inevitable in real-world applications.

• The experimental results on three datasets demonstrate the effectiveness and superiority of the proposed approach.

摘要

•A novel low-rank double dictionary learning (LRD2L) approach is proposed for robust image classification.•It integrates the low-rank matrix recovery technique with the class-specific and class-shared dictionary learning.•It can effectively handle the image corruptions in both training and testing samples, which are inevitable in real-world applications.•The experimental results on three datasets demonstrate the effectiveness and superiority of the proposed approach.

论文关键词：Low-rank dictionary learning,Class-specific dictionary,Class-shared dictionary,Image classification,Corrupted training samples,Robustness

论文评审过程：Received 1 November 2016, Revised 1 March 2017, Accepted 30 June 2017, Available online 5 July 2017, Version of Record 17 August 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.06.038