Fast and accurate computation of orthogonal moments for texture analysis

作者：

Highlights：

• Orthogonal moments are powerful descriptors for image classification.

• A fast and accurate computation is essential to guarantee their effectiveness.

• Computing moments from GLCMs enhance classification performance.

• The use of weighted moments results in better accuracy in some situations.

摘要

•Orthogonal moments are powerful descriptors for image classification.•A fast and accurate computation is essential to guarantee their effectiveness.•Computing moments from GLCMs enhance classification performance.•The use of weighted moments results in better accuracy in some situations.

论文关键词：Texture descriptor,Moment,Local binary pattern,Co-occurrence matrix,Classification

论文评审过程：Received 27 February 2018, Revised 4 June 2018, Accepted 15 June 2018, Available online 28 June 2018, Version of Record 3 July 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.06.012