Patch-based face recognition using a hierarchical multi-label matcher

作者：

Highlights：

• Developing a hierarchical multi-label based matcher for patch-based face recognition.

• Introducing majority voting, l1-regularized weighting, and decision rule to learn the relationships between patches.

• Applying the matcher to face recognition based on 2D face image and texture-lifted image.

摘要

•Developing a hierarchical multi-label based matcher for patch-based face recognition.•Introducing majority voting, l1-regularized weighting, and decision rule to learn the relationships between patches.•Applying the matcher to face recognition based on 2D face image and texture-lifted image.

论文关键词：Face recognition,Convolutional neural network,Hierarchical multi-label classification

论文评审过程：Received 16 September 2017, Revised 15 February 2018, Accepted 16 March 2018, Available online 28 March 2018, Version of Record 19 April 2018.

论文官网地址：https://doi.org/10.1016/j.imavis.2018.03.004