Detection and Classification of Rice Infestation with Rice Leaf Folder (<i>Cnaphalocrocis medinalis</i>) Using Hyperspectral Imaging Techniques

The detection of rice leaf folder (RLF) infestation usually depends on manual monitoring, and early infestations cannot be detected visually. To improve detection accuracy and reduce human error, we use push-broom hyperspectral sensors to scan rice images and use machine learning and deep neural lea...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Gui-Chou Liang, Yen-Chieh Ouyang, Shu-Mei Dai
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	rice rice leaf folder hyperspectral imaging band selection hyperspectral image classification target detection Science Q
Acceso en línea:	https://doaj.org/article/aa837ae3918046a99e2f6059af2077d6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:aa837ae3918046a99e2f6059af2077d6
record_format	dspace
spelling	oai:doaj.org-article:aa837ae3918046a99e2f6059af2077d62021-11-25T18:54:33ZDetection and Classification of Rice Infestation with Rice Leaf Folder (<i>Cnaphalocrocis medinalis</i>) Using Hyperspectral Imaging Techniques10.3390/rs132245872072-4292https://doaj.org/article/aa837ae3918046a99e2f6059af2077d62021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4587https://doaj.org/toc/2072-4292The detection of rice leaf folder (RLF) infestation usually depends on manual monitoring, and early infestations cannot be detected visually. To improve detection accuracy and reduce human error, we use push-broom hyperspectral sensors to scan rice images and use machine learning and deep neural learning methods to detect RLF-infested rice leaves. Different from traditional image processing methods, hyperspectral imaging data analysis is based on pixel-based classification and target recognition. Since the spectral information itself is a feature and can be considered a vector, deep learning neural networks do not need to use convolutional neural networks to extract features. To correctly detect the spectral image of rice leaves infested by RLF, we use the constrained energy minimization (CEM) method to suppress the background noise of the spectral image. A band selection method was utilized to reduce the computational energy consumption of using the full-band process, and six bands were selected as candidate bands. The following method is the band expansion process (BEP) method, which is utilized to expand the vector length to improve the problem of compressed spectral information for band selection. We use CEM and deep neural networks to detect defects in the spectral images of infected rice leaves and compare the performance of each in the full frequency band, frequency band selection, and frequency BEP. A total of 339 hyperspectral images were collected in this study; the results showed that six bands were sufficient for detecting early infestations of RLF, with a detection accuracy of 98% and a Dice similarity coefficient of 0.8, which provides advantages of commercialization of this field.Gui-Chou LiangYen-Chieh OuyangShu-Mei DaiMDPI AGarticlericerice leaf folderhyperspectral imagingband selectionhyperspectral image classificationtarget detectionScienceQENRemote Sensing, Vol 13, Iss 4587, p 4587 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	rice rice leaf folder hyperspectral imaging band selection hyperspectral image classification target detection Science Q
spellingShingle	rice rice leaf folder hyperspectral imaging band selection hyperspectral image classification target detection Science Q Gui-Chou Liang Yen-Chieh Ouyang Shu-Mei Dai Detection and Classification of Rice Infestation with Rice Leaf Folder (<i>Cnaphalocrocis medinalis</i>) Using Hyperspectral Imaging Techniques
description	The detection of rice leaf folder (RLF) infestation usually depends on manual monitoring, and early infestations cannot be detected visually. To improve detection accuracy and reduce human error, we use push-broom hyperspectral sensors to scan rice images and use machine learning and deep neural learning methods to detect RLF-infested rice leaves. Different from traditional image processing methods, hyperspectral imaging data analysis is based on pixel-based classification and target recognition. Since the spectral information itself is a feature and can be considered a vector, deep learning neural networks do not need to use convolutional neural networks to extract features. To correctly detect the spectral image of rice leaves infested by RLF, we use the constrained energy minimization (CEM) method to suppress the background noise of the spectral image. A band selection method was utilized to reduce the computational energy consumption of using the full-band process, and six bands were selected as candidate bands. The following method is the band expansion process (BEP) method, which is utilized to expand the vector length to improve the problem of compressed spectral information for band selection. We use CEM and deep neural networks to detect defects in the spectral images of infected rice leaves and compare the performance of each in the full frequency band, frequency band selection, and frequency BEP. A total of 339 hyperspectral images were collected in this study; the results showed that six bands were sufficient for detecting early infestations of RLF, with a detection accuracy of 98% and a Dice similarity coefficient of 0.8, which provides advantages of commercialization of this field.
format	article
author	Gui-Chou Liang Yen-Chieh Ouyang Shu-Mei Dai
author_facet	Gui-Chou Liang Yen-Chieh Ouyang Shu-Mei Dai
author_sort	Gui-Chou Liang
title	Detection and Classification of Rice Infestation with Rice Leaf Folder (<i>Cnaphalocrocis medinalis</i>) Using Hyperspectral Imaging Techniques
title_short	Detection and Classification of Rice Infestation with Rice Leaf Folder (<i>Cnaphalocrocis medinalis</i>) Using Hyperspectral Imaging Techniques
title_full	Detection and Classification of Rice Infestation with Rice Leaf Folder (<i>Cnaphalocrocis medinalis</i>) Using Hyperspectral Imaging Techniques
title_fullStr	Detection and Classification of Rice Infestation with Rice Leaf Folder (<i>Cnaphalocrocis medinalis</i>) Using Hyperspectral Imaging Techniques
title_full_unstemmed	Detection and Classification of Rice Infestation with Rice Leaf Folder (<i>Cnaphalocrocis medinalis</i>) Using Hyperspectral Imaging Techniques
title_sort	detection and classification of rice infestation with rice leaf folder (<i>cnaphalocrocis medinalis</i>) using hyperspectral imaging techniques
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/aa837ae3918046a99e2f6059af2077d6
work_keys_str_mv	AT guichouliang detectionandclassificationofriceinfestationwithriceleaffoldericnaphalocrocismedinalisiusinghyperspectralimagingtechniques AT yenchiehouyang detectionandclassificationofriceinfestationwithriceleaffoldericnaphalocrocismedinalisiusinghyperspectralimagingtechniques AT shumeidai detectionandclassificationofriceinfestationwithriceleaffoldericnaphalocrocismedinalisiusinghyperspectralimagingtechniques
_version_	1718410610974130176

Detection and Classification of Rice Infestation with Rice Leaf Folder (<i>Cnaphalocrocis medinalis</i>) Using Hyperspectral Imaging Techniques

Ejemplares similares