ETR: Enhancing transformation reduction for reducing dimensionality and classification complexity in hyperspectral images

作者：

Highlights：

• Present new approach to classify hyperspectral images (HIS).

• Propose a new feature extraction method, called ETR to boost HIS classification.

• ETR decreases scattering caused by noise, mixed pixels, and outliers of HSI.

• ETR smooths the classification process and accuracy and corrects pixels’ positions.

摘要

•Present new approach to classify hyperspectral images (HIS).•Propose a new feature extraction method, called ETR to boost HIS classification.•ETR decreases scattering caused by noise, mixed pixels, and outliers of HSI.•ETR smooths the classification process and accuracy and corrects pixels’ positions.

论文关键词：Feature extraction,Dimensionality reduction,Hyperspectral image,Classification,Feature fusion,Data distribution

论文评审过程：Received 13 July 2022, Revised 22 September 2022, Accepted 2 October 2022, Available online 11 October 2022, Version of Record 18 October 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118971