Cargando…

Fine-Grained Grape Leaf Diseases Recognition Method Based on Improved Lightweight Attention Network

Real-time dynamic monitoring of orchard grape leaf diseases can greatly improve the efficiency of disease control and is of great significance to the healthy and stable development of the grape industry. Traditional manual disease-monitoring methods are inefficient, labor-intensive, and ineffective....

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Peng, Niu, Tong, Mao, Yanru, Liu, Bin, Yang, Shuqin, He, Dongjian, Gao, Qiang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8569304/
https://www.ncbi.nlm.nih.gov/pubmed/34745172
http://dx.doi.org/10.3389/fpls.2021.738042
_version_ 1784594622160306176
author Wang, Peng
Niu, Tong
Mao, Yanru
Liu, Bin
Yang, Shuqin
He, Dongjian
Gao, Qiang
author_facet Wang, Peng
Niu, Tong
Mao, Yanru
Liu, Bin
Yang, Shuqin
He, Dongjian
Gao, Qiang
author_sort Wang, Peng
collection PubMed
description Real-time dynamic monitoring of orchard grape leaf diseases can greatly improve the efficiency of disease control and is of great significance to the healthy and stable development of the grape industry. Traditional manual disease-monitoring methods are inefficient, labor-intensive, and ineffective. Therefore, an efficient method is urgently needed for real-time dynamic monitoring of orchard grape diseases. The classical deep learning network can achieve high accuracy in recognizing grape leaf diseases; however, the large amount of model parameters requires huge computing resources, and it is difficult to deploy to actual application scenarios. To solve the above problems, a cross-channel interactive attention mechanism-based lightweight model (ECA-SNet) is proposed. First, based on 6,867 collected images of five common leaf diseases of measles, black rot, downy mildew, leaf blight, powdery mildew, and healthy leaves, image augmentation techniques are used to construct the training, validation, and test set. Then, with ShuffleNet-v2 as the backbone, an efficient channel attention strategy is introduced to strengthen the ability of the model for extracting fine-grained lesion features. Ultimately, the efficient lightweight model ECA-SNet is obtained by further simplifying the network layer structure. The model parameters amount of ECA-SNet 0.5× is only 24.6% of ShuffleNet-v2 1.0×, but the recognition accuracy is increased by 3.66 percentage points to 98.86%, and FLOPs are only 37.4 M, which means the performance is significantly better than other commonly used lightweight methods. Although the similarity of fine-grained features of different diseases image is relatively high, the average F1-score of the proposed lightweight model can still reach 0.988, which means the model has strong stability and anti-interference ability. The results show that the lightweight attention mechanism model proposed in this paper can efficiently use image fine-grained information to diagnose orchard grape leaf diseases at a low computing cost.
format Online
Article
Text
id pubmed-8569304
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-85693042021-11-06 Fine-Grained Grape Leaf Diseases Recognition Method Based on Improved Lightweight Attention Network Wang, Peng Niu, Tong Mao, Yanru Liu, Bin Yang, Shuqin He, Dongjian Gao, Qiang Front Plant Sci Plant Science Real-time dynamic monitoring of orchard grape leaf diseases can greatly improve the efficiency of disease control and is of great significance to the healthy and stable development of the grape industry. Traditional manual disease-monitoring methods are inefficient, labor-intensive, and ineffective. Therefore, an efficient method is urgently needed for real-time dynamic monitoring of orchard grape diseases. The classical deep learning network can achieve high accuracy in recognizing grape leaf diseases; however, the large amount of model parameters requires huge computing resources, and it is difficult to deploy to actual application scenarios. To solve the above problems, a cross-channel interactive attention mechanism-based lightweight model (ECA-SNet) is proposed. First, based on 6,867 collected images of five common leaf diseases of measles, black rot, downy mildew, leaf blight, powdery mildew, and healthy leaves, image augmentation techniques are used to construct the training, validation, and test set. Then, with ShuffleNet-v2 as the backbone, an efficient channel attention strategy is introduced to strengthen the ability of the model for extracting fine-grained lesion features. Ultimately, the efficient lightweight model ECA-SNet is obtained by further simplifying the network layer structure. The model parameters amount of ECA-SNet 0.5× is only 24.6% of ShuffleNet-v2 1.0×, but the recognition accuracy is increased by 3.66 percentage points to 98.86%, and FLOPs are only 37.4 M, which means the performance is significantly better than other commonly used lightweight methods. Although the similarity of fine-grained features of different diseases image is relatively high, the average F1-score of the proposed lightweight model can still reach 0.988, which means the model has strong stability and anti-interference ability. The results show that the lightweight attention mechanism model proposed in this paper can efficiently use image fine-grained information to diagnose orchard grape leaf diseases at a low computing cost. Frontiers Media S.A. 2021-10-22 /pmc/articles/PMC8569304/ /pubmed/34745172 http://dx.doi.org/10.3389/fpls.2021.738042 Text en Copyright © 2021 Wang, Niu, Mao, Liu, Yang, He and Gao. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Plant Science
Wang, Peng
Niu, Tong
Mao, Yanru
Liu, Bin
Yang, Shuqin
He, Dongjian
Gao, Qiang
Fine-Grained Grape Leaf Diseases Recognition Method Based on Improved Lightweight Attention Network
title Fine-Grained Grape Leaf Diseases Recognition Method Based on Improved Lightweight Attention Network
title_full Fine-Grained Grape Leaf Diseases Recognition Method Based on Improved Lightweight Attention Network
title_fullStr Fine-Grained Grape Leaf Diseases Recognition Method Based on Improved Lightweight Attention Network
title_full_unstemmed Fine-Grained Grape Leaf Diseases Recognition Method Based on Improved Lightweight Attention Network
title_short Fine-Grained Grape Leaf Diseases Recognition Method Based on Improved Lightweight Attention Network
title_sort fine-grained grape leaf diseases recognition method based on improved lightweight attention network
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8569304/
https://www.ncbi.nlm.nih.gov/pubmed/34745172
http://dx.doi.org/10.3389/fpls.2021.738042
work_keys_str_mv AT wangpeng finegrainedgrapeleafdiseasesrecognitionmethodbasedonimprovedlightweightattentionnetwork
AT niutong finegrainedgrapeleafdiseasesrecognitionmethodbasedonimprovedlightweightattentionnetwork
AT maoyanru finegrainedgrapeleafdiseasesrecognitionmethodbasedonimprovedlightweightattentionnetwork
AT liubin finegrainedgrapeleafdiseasesrecognitionmethodbasedonimprovedlightweightattentionnetwork
AT yangshuqin finegrainedgrapeleafdiseasesrecognitionmethodbasedonimprovedlightweightattentionnetwork
AT hedongjian finegrainedgrapeleafdiseasesrecognitionmethodbasedonimprovedlightweightattentionnetwork
AT gaoqiang finegrainedgrapeleafdiseasesrecognitionmethodbasedonimprovedlightweightattentionnetwork