Neutrosophic set based local binary pattern for texture classification

作者：

Highlights：

• The neutrosophic components are used to extract CLBP features.

• The neutrosophic components suppress noise and edges are detected more precisely.

• The use of neutrosophic truth and false sets has ensured more robust features.

• The proposed method improves the accuracy by about 24% on hand-crafted methods.

• It obtains up to 34% better results than the state-of-the-art deep learning methods.

摘要

•The neutrosophic components are used to extract CLBP features.•The neutrosophic components suppress noise and edges are detected more precisely.•The use of neutrosophic truth and false sets has ensured more robust features.•The proposed method improves the accuracy by about 24% on hand-crafted methods.•It obtains up to 34% better results than the state-of-the-art deep learning methods.

论文关键词：Neutrosophic set,Completed local binary pattern,Texture classification

论文评审过程：Received 11 February 2022, Revised 23 June 2022, Accepted 31 July 2022, Available online 4 August 2022, Version of Record 8 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118350