High-Accuracy Detection of Maize Leaf Diseases CNN Based on Multi-Pathway Activation Function Module

Maize leaf disease detection is an essential project in the maize planting stage. This paper proposes the convolutional neural network optimized by a Multi-Activation Function (MAF) module to detect maize leaf disease, aiming to increase the accuracy of traditional artificial intelligence methods. S...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yan Zhang, Shiyun Wa, Yutong Liu, Xiaoya Zhou, Pengshuo Sun, Qin Ma
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/d9dc4bcade9441d6a7bf487342f623a7
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:d9dc4bcade9441d6a7bf487342f623a7
record_format dspace
spelling oai:doaj.org-article:d9dc4bcade9441d6a7bf487342f623a72021-11-11T18:50:24ZHigh-Accuracy Detection of Maize Leaf Diseases CNN Based on Multi-Pathway Activation Function Module10.3390/rs132142182072-4292https://doaj.org/article/d9dc4bcade9441d6a7bf487342f623a72021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4218https://doaj.org/toc/2072-4292Maize leaf disease detection is an essential project in the maize planting stage. This paper proposes the convolutional neural network optimized by a Multi-Activation Function (MAF) module to detect maize leaf disease, aiming to increase the accuracy of traditional artificial intelligence methods. Since the disease dataset was insufficient, this paper adopts image pre-processing methods to extend and augment the disease samples. This paper uses transfer learning and warm-up method to accelerate the training. As a result, three kinds of maize diseases, including maculopathy, rust, and blight, could be detected efficiently and accurately. The accuracy of the proposed method in the validation set reached 97.41%. This paper carried out a baseline test to verify the effectiveness of the proposed method. First, three groups of CNNs with the best performance were selected. Then, ablation experiments were conducted on five CNNs. The results indicated that the performances of CNNs have been improved by adding the MAF module. In addition, the combination of Sigmoid, ReLU, and Mish showed the best performance on ResNet50. The accuracy can be improved by 2.33%, proving that the model proposed in this paper can be well applied to agricultural production.Yan ZhangShiyun WaYutong LiuXiaoya ZhouPengshuo SunQin MaMDPI AGarticlemaize leaf disease detectionactivation functionsgenerative adversarial networkconvolutional neural networkScienceQENRemote Sensing, Vol 13, Iss 4218, p 4218 (2021)
institution DOAJ
collection DOAJ
language EN
topic maize leaf disease detection
activation functions
generative adversarial network
convolutional neural network
Science
Q
spellingShingle maize leaf disease detection
activation functions
generative adversarial network
convolutional neural network
Science
Q
Yan Zhang
Shiyun Wa
Yutong Liu
Xiaoya Zhou
Pengshuo Sun
Qin Ma
High-Accuracy Detection of Maize Leaf Diseases CNN Based on Multi-Pathway Activation Function Module
description Maize leaf disease detection is an essential project in the maize planting stage. This paper proposes the convolutional neural network optimized by a Multi-Activation Function (MAF) module to detect maize leaf disease, aiming to increase the accuracy of traditional artificial intelligence methods. Since the disease dataset was insufficient, this paper adopts image pre-processing methods to extend and augment the disease samples. This paper uses transfer learning and warm-up method to accelerate the training. As a result, three kinds of maize diseases, including maculopathy, rust, and blight, could be detected efficiently and accurately. The accuracy of the proposed method in the validation set reached 97.41%. This paper carried out a baseline test to verify the effectiveness of the proposed method. First, three groups of CNNs with the best performance were selected. Then, ablation experiments were conducted on five CNNs. The results indicated that the performances of CNNs have been improved by adding the MAF module. In addition, the combination of Sigmoid, ReLU, and Mish showed the best performance on ResNet50. The accuracy can be improved by 2.33%, proving that the model proposed in this paper can be well applied to agricultural production.
format article
author Yan Zhang
Shiyun Wa
Yutong Liu
Xiaoya Zhou
Pengshuo Sun
Qin Ma
author_facet Yan Zhang
Shiyun Wa
Yutong Liu
Xiaoya Zhou
Pengshuo Sun
Qin Ma
author_sort Yan Zhang
title High-Accuracy Detection of Maize Leaf Diseases CNN Based on Multi-Pathway Activation Function Module
title_short High-Accuracy Detection of Maize Leaf Diseases CNN Based on Multi-Pathway Activation Function Module
title_full High-Accuracy Detection of Maize Leaf Diseases CNN Based on Multi-Pathway Activation Function Module
title_fullStr High-Accuracy Detection of Maize Leaf Diseases CNN Based on Multi-Pathway Activation Function Module
title_full_unstemmed High-Accuracy Detection of Maize Leaf Diseases CNN Based on Multi-Pathway Activation Function Module
title_sort high-accuracy detection of maize leaf diseases cnn based on multi-pathway activation function module
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/d9dc4bcade9441d6a7bf487342f623a7
work_keys_str_mv AT yanzhang highaccuracydetectionofmaizeleafdiseasescnnbasedonmultipathwayactivationfunctionmodule
AT shiyunwa highaccuracydetectionofmaizeleafdiseasescnnbasedonmultipathwayactivationfunctionmodule
AT yutongliu highaccuracydetectionofmaizeleafdiseasescnnbasedonmultipathwayactivationfunctionmodule
AT xiaoyazhou highaccuracydetectionofmaizeleafdiseasescnnbasedonmultipathwayactivationfunctionmodule
AT pengshuosun highaccuracydetectionofmaizeleafdiseasescnnbasedonmultipathwayactivationfunctionmodule
AT qinma highaccuracydetectionofmaizeleafdiseasescnnbasedonmultipathwayactivationfunctionmodule
_version_ 1718431733252096000