Feature discovery in NIR spectroscopy based Rocha pear classification

作者：

Highlights：

• The problem of Vis/NIR based fruit classification is considered.

• An innovative method of feature generation and selection is proposed.

• A total of 3050 Rocha Pear heterogeneous sample is analyzed.

• The proposed method outperforms existing methods while reduces the feature number.

• Selected features correspond to chemically meaningful wavelength bands.

摘要

•The problem of Vis/NIR based fruit classification is considered.•An innovative method of feature generation and selection is proposed.•A total of 3050 Rocha Pear heterogeneous sample is analyzed.•The proposed method outperforms existing methods while reduces the feature number.•Selected features correspond to chemically meaningful wavelength bands.

论文关键词：Feature extraction,Feature selection,Data analysis,Classification,Machine learning

论文评审过程：Received 18 December 2019, Revised 7 June 2020, Accepted 24 March 2021, Available online 31 March 2021, Version of Record 17 April 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114949