Few-shot cotton leaf spots disease classification based on metric learning

Abstract Background Cotton diceases seriously affect the yield and quality of cotton. The type of pest or disease suffered by cotton can be determined by the disease spots on the cotton leaves. This paper presents a few-shot learning framework that can be used for cotton leaf disease spot classifica...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Xihuizi Liang
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Cotton leaf disease Few-shot learning Support vector machine Disease identification Convolutional neural network Plant culture SB1-1110 Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/5ab48080197f4e999c955024fcbdabc7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5ab48080197f4e999c955024fcbdabc7
record_format	dspace
spelling	oai:doaj.org-article:5ab48080197f4e999c955024fcbdabc72021-11-14T12:11:16ZFew-shot cotton leaf spots disease classification based on metric learning10.1186/s13007-021-00813-71746-4811https://doaj.org/article/5ab48080197f4e999c955024fcbdabc72021-11-01T00:00:00Zhttps://doi.org/10.1186/s13007-021-00813-7https://doaj.org/toc/1746-4811Abstract Background Cotton diceases seriously affect the yield and quality of cotton. The type of pest or disease suffered by cotton can be determined by the disease spots on the cotton leaves. This paper presents a few-shot learning framework that can be used for cotton leaf disease spot classification task. This can be used in preventing and controlling cotton diseases timely. First, disease spots on cotton leaf’s disease images are segmented by different methods, compared by using support vector machine (SVM) method and threshold segmentation, and discussed the suitable one. Then, with segmented disease spot images as input, a disease spot dataset is established, and the cotton leaf disease spots were classified using a classical convolutional neural network classifier, the structure and framework of convolutional neural network had been designed. At last, the features of two different images are extracted by a parallel two-way convolutional neural network with weight sharing. Then, the network uses a loss function to learn the metric space, in which similar leaf samples are close to each other and different leaf samples are far away from each other. In summary, this work can be regarded as a significang reference and the benchmark comparison for the follow-up studies of few-shot learning tasks in the agricultural field. Results To achieve the classification of cotton leaf spots by small sample learning, a metric-based learning method was developed to extract cotton leaf spot features and classify the sick leaves. The threshold segmentation and SVM were compared in the extracting of leaf spot. The results showed that both of these two method can extract the leaf spot in a good performance, SVM expented more time, but the leaf spot which extracted from SVM was much more suitable for classifying, thus SVM method can retain much more information of leaf spot, such as color, shape, textures, ect, which can help classficating the leaf spot. In the process of leaf spot classification, the two-way parallel convolutional neural network was established for building the leaf spot feature extractor, and feature classifier is constructed. After establishing the metric space, KNN was used as the spot classifier, and for the construction of convolutional neural networks, commonly used models were selected for comparison, and a spatial structure optimizer (SSO) is introduced for local optimization of the model, include Vgg, DesenNet, and ResNet. Experimentally, it is demonstrated that the classification accuracy of DenseNet is the highest, compared to the other two networks, and the classification accuracy of S-DenseNet is 7.7% higher then DenseNet on average for different number of steps. Conclusions As the step increasing, the accuracy of DesenNet, and ResNet are all improved, and after using SSO, each of these neural networks can achieved better performance. But The extent of increase varies, DesenNet with SSO had been improved the most obviously.Xihuizi LiangBMCarticleCotton leaf diseaseFew-shot learningSupport vector machineDisease identificationConvolutional neural networkPlant cultureSB1-1110Biology (General)QH301-705.5ENPlant Methods, Vol 17, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Cotton leaf disease Few-shot learning Support vector machine Disease identification Convolutional neural network Plant culture SB1-1110 Biology (General) QH301-705.5
spellingShingle	Cotton leaf disease Few-shot learning Support vector machine Disease identification Convolutional neural network Plant culture SB1-1110 Biology (General) QH301-705.5 Xihuizi Liang Few-shot cotton leaf spots disease classification based on metric learning
description	Abstract Background Cotton diceases seriously affect the yield and quality of cotton. The type of pest or disease suffered by cotton can be determined by the disease spots on the cotton leaves. This paper presents a few-shot learning framework that can be used for cotton leaf disease spot classification task. This can be used in preventing and controlling cotton diseases timely. First, disease spots on cotton leaf’s disease images are segmented by different methods, compared by using support vector machine (SVM) method and threshold segmentation, and discussed the suitable one. Then, with segmented disease spot images as input, a disease spot dataset is established, and the cotton leaf disease spots were classified using a classical convolutional neural network classifier, the structure and framework of convolutional neural network had been designed. At last, the features of two different images are extracted by a parallel two-way convolutional neural network with weight sharing. Then, the network uses a loss function to learn the metric space, in which similar leaf samples are close to each other and different leaf samples are far away from each other. In summary, this work can be regarded as a significang reference and the benchmark comparison for the follow-up studies of few-shot learning tasks in the agricultural field. Results To achieve the classification of cotton leaf spots by small sample learning, a metric-based learning method was developed to extract cotton leaf spot features and classify the sick leaves. The threshold segmentation and SVM were compared in the extracting of leaf spot. The results showed that both of these two method can extract the leaf spot in a good performance, SVM expented more time, but the leaf spot which extracted from SVM was much more suitable for classifying, thus SVM method can retain much more information of leaf spot, such as color, shape, textures, ect, which can help classficating the leaf spot. In the process of leaf spot classification, the two-way parallel convolutional neural network was established for building the leaf spot feature extractor, and feature classifier is constructed. After establishing the metric space, KNN was used as the spot classifier, and for the construction of convolutional neural networks, commonly used models were selected for comparison, and a spatial structure optimizer (SSO) is introduced for local optimization of the model, include Vgg, DesenNet, and ResNet. Experimentally, it is demonstrated that the classification accuracy of DenseNet is the highest, compared to the other two networks, and the classification accuracy of S-DenseNet is 7.7% higher then DenseNet on average for different number of steps. Conclusions As the step increasing, the accuracy of DesenNet, and ResNet are all improved, and after using SSO, each of these neural networks can achieved better performance. But The extent of increase varies, DesenNet with SSO had been improved the most obviously.
format	article
author	Xihuizi Liang
author_facet	Xihuizi Liang
author_sort	Xihuizi Liang
title	Few-shot cotton leaf spots disease classification based on metric learning
title_short	Few-shot cotton leaf spots disease classification based on metric learning
title_full	Few-shot cotton leaf spots disease classification based on metric learning
title_fullStr	Few-shot cotton leaf spots disease classification based on metric learning
title_full_unstemmed	Few-shot cotton leaf spots disease classification based on metric learning
title_sort	few-shot cotton leaf spots disease classification based on metric learning
publisher	BMC
publishDate	2021
url	https://doaj.org/article/5ab48080197f4e999c955024fcbdabc7
work_keys_str_mv	AT xihuiziliang fewshotcottonleafspotsdiseaseclassificationbasedonmetriclearning
_version_	1718429404238970880

Few-shot cotton leaf spots disease classification based on metric learning

Ejemplares similares