An Automatic Light Stress Grading Architecture Based on Feature Optimization and Convolutional Neural Network

The identification of light stress is crucial for light control in plant factories. Image-based lighting classification of leafy vegetables has exhibited remarkable performance with high convenience and economy. Convolutional Neural Network (CNN) has been widely used for crop image analysis because...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xia Hao, Man Zhang, Tianru Zhou, Xuchao Guo, Federico Tomasetto, Yuxin Tong, Minjuan Wang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	light stress grading fine-grained visual classification inter-class variance intra-class variance feature mapping Agriculture (General) S1-972
Acceso en línea:	https://doaj.org/article/6c0bf8ac33c444ad9399cbaa3fd3cd8b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6c0bf8ac33c444ad9399cbaa3fd3cd8b
record_format	dspace
spelling	oai:doaj.org-article:6c0bf8ac33c444ad9399cbaa3fd3cd8b2021-11-25T15:59:41ZAn Automatic Light Stress Grading Architecture Based on Feature Optimization and Convolutional Neural Network10.3390/agriculture111111262077-0472https://doaj.org/article/6c0bf8ac33c444ad9399cbaa3fd3cd8b2021-11-01T00:00:00Zhttps://www.mdpi.com/2077-0472/11/11/1126https://doaj.org/toc/2077-0472The identification of light stress is crucial for light control in plant factories. Image-based lighting classification of leafy vegetables has exhibited remarkable performance with high convenience and economy. Convolutional Neural Network (CNN) has been widely used for crop image analysis because of its architecture, high accuracy and efficiency. Among them, large intra-class differences and small inter-class differences are important factors affecting crop identification and a critical challenge for fine-grained classification tasks based on CNN. To address this problem, we took the Lettuce (<i>Lactuca sativa</i> L.) widely grown in plant factories as the research object and constructed a leaf image set containing four stress levels. Then a light stress grading model combined with classic pre-trained CNN and Triplet loss function is constructed, which is named Tr-CNN. The model uses the Triplet loss function to constrain the distance of images in the feature space, which can reduce the Euclidean distance of the samples from the same class and increase the heterogeneous Euclidean distance. Multiple sets of experimental results indicate that the model proposed in this paper (Tr-CNN) has obvious advantages in light stress grading dataset and generalized dataset.Xia HaoMan ZhangTianru ZhouXuchao GuoFederico TomasettoYuxin TongMinjuan WangMDPI AGarticlelight stress gradingfine-grained visual classificationinter-class varianceintra-class variancefeature mappingAgriculture (General)S1-972ENAgriculture, Vol 11, Iss 1126, p 1126 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	light stress grading fine-grained visual classification inter-class variance intra-class variance feature mapping Agriculture (General) S1-972
spellingShingle	light stress grading fine-grained visual classification inter-class variance intra-class variance feature mapping Agriculture (General) S1-972 Xia Hao Man Zhang Tianru Zhou Xuchao Guo Federico Tomasetto Yuxin Tong Minjuan Wang An Automatic Light Stress Grading Architecture Based on Feature Optimization and Convolutional Neural Network
description	The identification of light stress is crucial for light control in plant factories. Image-based lighting classification of leafy vegetables has exhibited remarkable performance with high convenience and economy. Convolutional Neural Network (CNN) has been widely used for crop image analysis because of its architecture, high accuracy and efficiency. Among them, large intra-class differences and small inter-class differences are important factors affecting crop identification and a critical challenge for fine-grained classification tasks based on CNN. To address this problem, we took the Lettuce (<i>Lactuca sativa</i> L.) widely grown in plant factories as the research object and constructed a leaf image set containing four stress levels. Then a light stress grading model combined with classic pre-trained CNN and Triplet loss function is constructed, which is named Tr-CNN. The model uses the Triplet loss function to constrain the distance of images in the feature space, which can reduce the Euclidean distance of the samples from the same class and increase the heterogeneous Euclidean distance. Multiple sets of experimental results indicate that the model proposed in this paper (Tr-CNN) has obvious advantages in light stress grading dataset and generalized dataset.
format	article
author	Xia Hao Man Zhang Tianru Zhou Xuchao Guo Federico Tomasetto Yuxin Tong Minjuan Wang
author_facet	Xia Hao Man Zhang Tianru Zhou Xuchao Guo Federico Tomasetto Yuxin Tong Minjuan Wang
author_sort	Xia Hao
title	An Automatic Light Stress Grading Architecture Based on Feature Optimization and Convolutional Neural Network
title_short	An Automatic Light Stress Grading Architecture Based on Feature Optimization and Convolutional Neural Network
title_full	An Automatic Light Stress Grading Architecture Based on Feature Optimization and Convolutional Neural Network
title_fullStr	An Automatic Light Stress Grading Architecture Based on Feature Optimization and Convolutional Neural Network
title_full_unstemmed	An Automatic Light Stress Grading Architecture Based on Feature Optimization and Convolutional Neural Network
title_sort	automatic light stress grading architecture based on feature optimization and convolutional neural network
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/6c0bf8ac33c444ad9399cbaa3fd3cd8b
work_keys_str_mv	AT xiahao anautomaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT manzhang anautomaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT tianruzhou anautomaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT xuchaoguo anautomaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT federicotomasetto anautomaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT yuxintong anautomaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT minjuanwang anautomaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT xiahao automaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT manzhang automaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT tianruzhou automaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT xuchaoguo automaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT federicotomasetto automaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT yuxintong automaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork AT minjuanwang automaticlightstressgradingarchitecturebasedonfeatureoptimizationandconvolutionalneuralnetwork
_version_	1718413383608303616

An Automatic Light Stress Grading Architecture Based on Feature Optimization and Convolutional Neural Network

Ejemplares similares