Using Deep Convolutional Neural Networks for Image-Based Diagnosis of Nutrient Deficiencies in Rice
Symptoms of nutrient deficiencies in rice plants often appear on the leaves. The leaf color and shape, therefore, can be used to diagnose nutrient deficiencies in rice. Image classification is an efficient and fast approach for this diagnosis task. Deep convolutional neural networks (DCNNs) have bee...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2020-01-01
|
Series: | Computational Intelligence and Neuroscience |
Online Access: | http://dx.doi.org/10.1155/2020/7307252 |
id |
doaj-4950b656073548aab1b8ccbf2a227df8 |
---|---|
record_format |
Article |
spelling |
doaj-4950b656073548aab1b8ccbf2a227df82020-11-25T03:27:57ZengHindawi LimitedComputational Intelligence and Neuroscience1687-52651687-52732020-01-01202010.1155/2020/73072527307252Using Deep Convolutional Neural Networks for Image-Based Diagnosis of Nutrient Deficiencies in RiceZhe Xu0Xi Guo1Anfan Zhu2Xiaolin He3Xiaomin Zhao4Yi Han5Roshan Subedi6College of Forestry, Jiangxi Agricultural University, Nanchang 330045, ChinaKey Laboratory of Poyang Lake Watershed Agricultural Resources and Ecology of Jiangxi Province, Jiangxi Agricultural University, Nanchang 330045, ChinaSoil and Fertilization Technology Extension Station of Jiangxi Province, Nanchang 330045, ChinaSoil and Fertilization Technology Extension Station of Jiangxi Province, Nanchang 330045, ChinaKey Laboratory of Poyang Lake Watershed Agricultural Resources and Ecology of Jiangxi Province, Jiangxi Agricultural University, Nanchang 330045, ChinaKey Laboratory of Poyang Lake Watershed Agricultural Resources and Ecology of Jiangxi Province, Jiangxi Agricultural University, Nanchang 330045, ChinaKey Laboratory of Poyang Lake Watershed Agricultural Resources and Ecology of Jiangxi Province, Jiangxi Agricultural University, Nanchang 330045, ChinaSymptoms of nutrient deficiencies in rice plants often appear on the leaves. The leaf color and shape, therefore, can be used to diagnose nutrient deficiencies in rice. Image classification is an efficient and fast approach for this diagnosis task. Deep convolutional neural networks (DCNNs) have been proven to be effective in image classification, but their use to identify nutrient deficiencies in rice has received little attention. In the present study, we explore the accuracy of different DCNNs for diagnosis of nutrient deficiencies in rice. A total of 1818 photographs of plant leaves were obtained via hydroponic experiments to cover full nutrition and 10 classes of nutrient deficiencies. The photographs were divided into training, validation, and test sets in a 3 : 1 : 1 ratio. Fine-tuning was performed to evaluate four state-of-the-art DCNNs: Inception-v3, ResNet with 50 layers, NasNet-Large, and DenseNet with 121 layers. All the DCNNs obtained validation and test accuracies of over 90%, with DenseNet121 performing best (validation accuracy = 98.62 ± 0.57%; test accuracy = 97.44 ± 0.57%). The performance of the DCNNs was validated by comparison to color feature with support vector machine and histogram of oriented gradient with support vector machine. This study demonstrates that DCNNs provide an effective approach to diagnose nutrient deficiencies in rice.http://dx.doi.org/10.1155/2020/7307252 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhe Xu Xi Guo Anfan Zhu Xiaolin He Xiaomin Zhao Yi Han Roshan Subedi |
spellingShingle |
Zhe Xu Xi Guo Anfan Zhu Xiaolin He Xiaomin Zhao Yi Han Roshan Subedi Using Deep Convolutional Neural Networks for Image-Based Diagnosis of Nutrient Deficiencies in Rice Computational Intelligence and Neuroscience |
author_facet |
Zhe Xu Xi Guo Anfan Zhu Xiaolin He Xiaomin Zhao Yi Han Roshan Subedi |
author_sort |
Zhe Xu |
title |
Using Deep Convolutional Neural Networks for Image-Based Diagnosis of Nutrient Deficiencies in Rice |
title_short |
Using Deep Convolutional Neural Networks for Image-Based Diagnosis of Nutrient Deficiencies in Rice |
title_full |
Using Deep Convolutional Neural Networks for Image-Based Diagnosis of Nutrient Deficiencies in Rice |
title_fullStr |
Using Deep Convolutional Neural Networks for Image-Based Diagnosis of Nutrient Deficiencies in Rice |
title_full_unstemmed |
Using Deep Convolutional Neural Networks for Image-Based Diagnosis of Nutrient Deficiencies in Rice |
title_sort |
using deep convolutional neural networks for image-based diagnosis of nutrient deficiencies in rice |
publisher |
Hindawi Limited |
series |
Computational Intelligence and Neuroscience |
issn |
1687-5265 1687-5273 |
publishDate |
2020-01-01 |
description |
Symptoms of nutrient deficiencies in rice plants often appear on the leaves. The leaf color and shape, therefore, can be used to diagnose nutrient deficiencies in rice. Image classification is an efficient and fast approach for this diagnosis task. Deep convolutional neural networks (DCNNs) have been proven to be effective in image classification, but their use to identify nutrient deficiencies in rice has received little attention. In the present study, we explore the accuracy of different DCNNs for diagnosis of nutrient deficiencies in rice. A total of 1818 photographs of plant leaves were obtained via hydroponic experiments to cover full nutrition and 10 classes of nutrient deficiencies. The photographs were divided into training, validation, and test sets in a 3 : 1 : 1 ratio. Fine-tuning was performed to evaluate four state-of-the-art DCNNs: Inception-v3, ResNet with 50 layers, NasNet-Large, and DenseNet with 121 layers. All the DCNNs obtained validation and test accuracies of over 90%, with DenseNet121 performing best (validation accuracy = 98.62 ± 0.57%; test accuracy = 97.44 ± 0.57%). The performance of the DCNNs was validated by comparison to color feature with support vector machine and histogram of oriented gradient with support vector machine. This study demonstrates that DCNNs provide an effective approach to diagnose nutrient deficiencies in rice. |
url |
http://dx.doi.org/10.1155/2020/7307252 |
work_keys_str_mv |
AT zhexu usingdeepconvolutionalneuralnetworksforimagebaseddiagnosisofnutrientdeficienciesinrice AT xiguo usingdeepconvolutionalneuralnetworksforimagebaseddiagnosisofnutrientdeficienciesinrice AT anfanzhu usingdeepconvolutionalneuralnetworksforimagebaseddiagnosisofnutrientdeficienciesinrice AT xiaolinhe usingdeepconvolutionalneuralnetworksforimagebaseddiagnosisofnutrientdeficienciesinrice AT xiaominzhao usingdeepconvolutionalneuralnetworksforimagebaseddiagnosisofnutrientdeficienciesinrice AT yihan usingdeepconvolutionalneuralnetworksforimagebaseddiagnosisofnutrientdeficienciesinrice AT roshansubedi usingdeepconvolutionalneuralnetworksforimagebaseddiagnosisofnutrientdeficienciesinrice |
_version_ |
1715207328478789632 |