Research on Maize Disease Recognition Method Based on Improved ResNet50

In order to solve the problem of accuracy and speed of disease identification in real-time spraying operation in maize field, an improved ResNet50 maize disease identification model was proposed. Firstly, this paper uses the Adam algorithm to optimize the model, adjusts the learning strategy through...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Guowei Wang, Haiye Yu, Yuanyuan Sui
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Telecommunication TK5101-6720
Acceso en línea:	https://doaj.org/article/1364bc7c10d2402786fbd78fe704c9f1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1364bc7c10d2402786fbd78fe704c9f1
record_format	dspace
spelling	oai:doaj.org-article:1364bc7c10d2402786fbd78fe704c9f12021-11-08T02:36:23ZResearch on Maize Disease Recognition Method Based on Improved ResNet501875-905X10.1155/2021/9110866https://doaj.org/article/1364bc7c10d2402786fbd78fe704c9f12021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/9110866https://doaj.org/toc/1875-905XIn order to solve the problem of accuracy and speed of disease identification in real-time spraying operation in maize field, an improved ResNet50 maize disease identification model was proposed. Firstly, this paper uses the Adam algorithm to optimize the model, adjusts the learning strategy through the inclined triangle learning rate, increases L2 regularization to reduce over fitting, and adopts exit strategy and ReLU incentive function. Then, the first convolution kernel of the ResNet50 model is modified into three 3 x 3 small convolution kernels. Finally, the ratio of training set to verification set is 3 : 1. Through experimental comparison, the recognition accuracy of the maize disease recognition model proposed in this paper is higher than that of other models. The image recognition accuracy in the data set is 98.52%, the image recognition accuracy in the farmland is 97.826%, and the average recognition speed is 204 ms, which meets the accuracy and speed requirements of maize field spraying operation and provides technical support for the research of maize field spraying equipment.Guowei WangHaiye YuYuanyuan SuiHindawi LimitedarticleTelecommunicationTK5101-6720ENMobile Information Systems, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Telecommunication TK5101-6720
spellingShingle	Telecommunication TK5101-6720 Guowei Wang Haiye Yu Yuanyuan Sui Research on Maize Disease Recognition Method Based on Improved ResNet50
description	In order to solve the problem of accuracy and speed of disease identification in real-time spraying operation in maize field, an improved ResNet50 maize disease identification model was proposed. Firstly, this paper uses the Adam algorithm to optimize the model, adjusts the learning strategy through the inclined triangle learning rate, increases L2 regularization to reduce over fitting, and adopts exit strategy and ReLU incentive function. Then, the first convolution kernel of the ResNet50 model is modified into three 3 x 3 small convolution kernels. Finally, the ratio of training set to verification set is 3 : 1. Through experimental comparison, the recognition accuracy of the maize disease recognition model proposed in this paper is higher than that of other models. The image recognition accuracy in the data set is 98.52%, the image recognition accuracy in the farmland is 97.826%, and the average recognition speed is 204 ms, which meets the accuracy and speed requirements of maize field spraying operation and provides technical support for the research of maize field spraying equipment.
format	article
author	Guowei Wang Haiye Yu Yuanyuan Sui
author_facet	Guowei Wang Haiye Yu Yuanyuan Sui
author_sort	Guowei Wang
title	Research on Maize Disease Recognition Method Based on Improved ResNet50
title_short	Research on Maize Disease Recognition Method Based on Improved ResNet50
title_full	Research on Maize Disease Recognition Method Based on Improved ResNet50
title_fullStr	Research on Maize Disease Recognition Method Based on Improved ResNet50
title_full_unstemmed	Research on Maize Disease Recognition Method Based on Improved ResNet50
title_sort	research on maize disease recognition method based on improved resnet50
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/1364bc7c10d2402786fbd78fe704c9f1
work_keys_str_mv	AT guoweiwang researchonmaizediseaserecognitionmethodbasedonimprovedresnet50 AT haiyeyu researchonmaizediseaserecognitionmethodbasedonimprovedresnet50 AT yuanyuansui researchonmaizediseaserecognitionmethodbasedonimprovedresnet50
_version_	1718443067362508800

Research on Maize Disease Recognition Method Based on Improved ResNet50

Ejemplares similares