Data-driven techniques for smoothing histograms of local binary patterns

作者：

Highlights：

• This paper proposes data-driven techniques for smoothing LBP histograms.

• The proposed smoothing techniques cover unsupervised and supervised variants.

• The techniques are evaluated on material categorization and face recognition.

• Histogram smoothing is beneficial especially in small-sample-size scenarios.

摘要

Highlights•This paper proposes data-driven techniques for smoothing LBP histograms.•The proposed smoothing techniques cover unsupervised and supervised variants.•The techniques are evaluated on material categorization and face recognition.•Histogram smoothing is beneficial especially in small-sample-size scenarios.

论文关键词：Local binary patterns,Local binarized descriptors,Histogram,Soft-assignment,Kernel density estimation,Histogram smoothing

论文评审过程：Received 11 August 2015, Revised 27 June 2016, Accepted 28 June 2016, Available online 29 June 2016, Version of Record 16 July 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.06.029