Label and orthogonality regularized non-negative matrix factorization for image classification

作者：

Highlights：

•

• Orthogonality guarantees parts-based representation and discriminant localization.

• Label consistence enhances discriminant ability of LONMF for image classification.

• The designed linear classifier increases the effectiveness for image classification.

• Experiments on the challenging databases well validate the performance of LONMF.

摘要

•Orthogonality guarantees parts-based representation and discriminant localization.•Label consistence enhances discriminant ability of LONMF for image classification.•The designed linear classifier increases the effectiveness for image classification.•Experiments on the challenging databases well validate the performance of LONMF.

论文关键词：Non-negative matrix factorization (NMF),Orthogonal property,Label consistence,Image classification

论文评审过程：Received 30 May 2017, Revised 4 January 2018, Accepted 4 January 2018, Available online 10 January 2018, Version of Record 4 February 2018.

论文官网地址：https://doi.org/10.1016/j.image.2018.01.001