A Discriminative Model for Early Detection of Anthracnose in Strawberry Plants Based on Hyperspectral Imaging Technology
Strawberry anthracnose, caused by <i>Colletotrichum</i> spp., is a major disease that causes tremendous damage to cultivated strawberry plants (<i>Fragaria</i> × <i>ananassa</i> Duch.). Examining and distinguishing plants potentially carrying the pathogen is one o...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/18/4640 |
_version_ | 1797577207548215296 |
---|---|
author | Chao Liu Yifei Cao Ejiao Wu Risheng Yang Huanliang Xu Yushan Qiao |
author_facet | Chao Liu Yifei Cao Ejiao Wu Risheng Yang Huanliang Xu Yushan Qiao |
author_sort | Chao Liu |
collection | DOAJ |
description | Strawberry anthracnose, caused by <i>Colletotrichum</i> spp., is a major disease that causes tremendous damage to cultivated strawberry plants (<i>Fragaria</i> × <i>ananassa</i> Duch.). Examining and distinguishing plants potentially carrying the pathogen is one of the most effective ways to prevent and control strawberry anthracnose disease. Herein, we used this method on <i>Colletotrichum gloeosporioides</i> at the crown site on indoor strawberry plants and established a classification and distinguishing model based on measurement of the spectral and textural characteristics of the disease-free zone near the disease center. The results, based on the successive projection algorithm (SPA), competitive adaptive reweighted sampling (CARS), and interval random frog (IRF), extracted 5, 14, and 11 characteristic wavelengths, respectively. The SPA extracted fewer effective characteristic wavelengths, while IRF covered more information. A total of 12 dimensional texture features (TFs) were extracted from the first three minimum noise fraction (MNF) images using a grayscale co-occurrence matrix (GLCM). The combined dataset modeling of spectral and TFs performed better than single-feature modeling. The accuracy rates of the IRF + TF + BP model test set for healthy, asymptomatic, and symptomatic samples were 99.1%, 93.5%, and 94.5%, the recall rates were 100%, 94%, and 93%, and the F1 scores were 0.9955, 0.9375, and 0.9374, respectively. The total modeling time was 10.9 s, meaning that this model demonstrated the best comprehensive performance of all the constructed models. The model lays a technical foundation for the early, non-destructive detection of strawberry anthracnose. |
first_indexed | 2024-03-10T22:04:50Z |
format | Article |
id | doaj.art-ea775b62cccb465f8febbca47add3312 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T22:04:50Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-ea775b62cccb465f8febbca47add33122023-11-19T12:50:35ZengMDPI AGRemote Sensing2072-42922023-09-011518464010.3390/rs15184640A Discriminative Model for Early Detection of Anthracnose in Strawberry Plants Based on Hyperspectral Imaging TechnologyChao Liu0Yifei Cao1Ejiao Wu2Risheng Yang3Huanliang Xu4Yushan Qiao5College of Horticulture, Nanjing Agricultural University, Nanjing 210014, ChinaCollege of Horticulture, Nanjing Agricultural University, Nanjing 210014, ChinaJiangsu Key Laboratory for Horticultural Crop Genetic Improvement, Institute of Pomology, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, ChinaCollege of Horticulture, Nanjing Agricultural University, Nanjing 210014, ChinaCollege of Horticulture, Nanjing Agricultural University, Nanjing 210014, ChinaCollege of Horticulture, Nanjing Agricultural University, Nanjing 210014, ChinaStrawberry anthracnose, caused by <i>Colletotrichum</i> spp., is a major disease that causes tremendous damage to cultivated strawberry plants (<i>Fragaria</i> × <i>ananassa</i> Duch.). Examining and distinguishing plants potentially carrying the pathogen is one of the most effective ways to prevent and control strawberry anthracnose disease. Herein, we used this method on <i>Colletotrichum gloeosporioides</i> at the crown site on indoor strawberry plants and established a classification and distinguishing model based on measurement of the spectral and textural characteristics of the disease-free zone near the disease center. The results, based on the successive projection algorithm (SPA), competitive adaptive reweighted sampling (CARS), and interval random frog (IRF), extracted 5, 14, and 11 characteristic wavelengths, respectively. The SPA extracted fewer effective characteristic wavelengths, while IRF covered more information. A total of 12 dimensional texture features (TFs) were extracted from the first three minimum noise fraction (MNF) images using a grayscale co-occurrence matrix (GLCM). The combined dataset modeling of spectral and TFs performed better than single-feature modeling. The accuracy rates of the IRF + TF + BP model test set for healthy, asymptomatic, and symptomatic samples were 99.1%, 93.5%, and 94.5%, the recall rates were 100%, 94%, and 93%, and the F1 scores were 0.9955, 0.9375, and 0.9374, respectively. The total modeling time was 10.9 s, meaning that this model demonstrated the best comprehensive performance of all the constructed models. The model lays a technical foundation for the early, non-destructive detection of strawberry anthracnose.https://www.mdpi.com/2072-4292/15/18/4640hyperspectralstrawberry anthracnosecharacteristic wavelengthtexture featuresconvolutional neural network |
spellingShingle | Chao Liu Yifei Cao Ejiao Wu Risheng Yang Huanliang Xu Yushan Qiao A Discriminative Model for Early Detection of Anthracnose in Strawberry Plants Based on Hyperspectral Imaging Technology Remote Sensing hyperspectral strawberry anthracnose characteristic wavelength texture features convolutional neural network |
title | A Discriminative Model for Early Detection of Anthracnose in Strawberry Plants Based on Hyperspectral Imaging Technology |
title_full | A Discriminative Model for Early Detection of Anthracnose in Strawberry Plants Based on Hyperspectral Imaging Technology |
title_fullStr | A Discriminative Model for Early Detection of Anthracnose in Strawberry Plants Based on Hyperspectral Imaging Technology |
title_full_unstemmed | A Discriminative Model for Early Detection of Anthracnose in Strawberry Plants Based on Hyperspectral Imaging Technology |
title_short | A Discriminative Model for Early Detection of Anthracnose in Strawberry Plants Based on Hyperspectral Imaging Technology |
title_sort | discriminative model for early detection of anthracnose in strawberry plants based on hyperspectral imaging technology |
topic | hyperspectral strawberry anthracnose characteristic wavelength texture features convolutional neural network |
url | https://www.mdpi.com/2072-4292/15/18/4640 |
work_keys_str_mv | AT chaoliu adiscriminativemodelforearlydetectionofanthracnoseinstrawberryplantsbasedonhyperspectralimagingtechnology AT yifeicao adiscriminativemodelforearlydetectionofanthracnoseinstrawberryplantsbasedonhyperspectralimagingtechnology AT ejiaowu adiscriminativemodelforearlydetectionofanthracnoseinstrawberryplantsbasedonhyperspectralimagingtechnology AT rishengyang adiscriminativemodelforearlydetectionofanthracnoseinstrawberryplantsbasedonhyperspectralimagingtechnology AT huanliangxu adiscriminativemodelforearlydetectionofanthracnoseinstrawberryplantsbasedonhyperspectralimagingtechnology AT yushanqiao adiscriminativemodelforearlydetectionofanthracnoseinstrawberryplantsbasedonhyperspectralimagingtechnology AT chaoliu discriminativemodelforearlydetectionofanthracnoseinstrawberryplantsbasedonhyperspectralimagingtechnology AT yifeicao discriminativemodelforearlydetectionofanthracnoseinstrawberryplantsbasedonhyperspectralimagingtechnology AT ejiaowu discriminativemodelforearlydetectionofanthracnoseinstrawberryplantsbasedonhyperspectralimagingtechnology AT rishengyang discriminativemodelforearlydetectionofanthracnoseinstrawberryplantsbasedonhyperspectralimagingtechnology AT huanliangxu discriminativemodelforearlydetectionofanthracnoseinstrawberryplantsbasedonhyperspectralimagingtechnology AT yushanqiao discriminativemodelforearlydetectionofanthracnoseinstrawberryplantsbasedonhyperspectralimagingtechnology |