Early detection of grapevine diseases using pre-trained Convolutional Neural Networks

This paper proposes to apply pre-trained Convolutional Neural Networks (CNN) for the early detection of two common grapevine diseases: peronospora and o´ıdio. These diseases present similar symptoms and are of great viticultural importance. Our objective is to train a CNN using transfer learning tec...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Rios, Cristian Emmanuel, Estrebou, César Armando, Frati, Fernando Emmanuel
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2023
Materias:
Ciencias Informáticas
Deep Learning
Convolutional Neural Networks
Object Detection
Edge Computing
Inclusive Inteligent Systems
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/155434
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-155434
record_format dspace
spelling I19-R120-10915-1554342023-07-11T20:01:33Z http://sedici.unlp.edu.ar/handle/10915/155434 isbn:978-950-34-2271-7 Early detection of grapevine diseases using pre-trained Convolutional Neural Networks Rios, Cristian Emmanuel Estrebou, César Armando Frati, Fernando Emmanuel 2023-06 2023 2023-07-11T17:45:16Z en Ciencias Informáticas Deep Learning Convolutional Neural Networks Object Detection Edge Computing Inclusive Inteligent Systems This paper proposes to apply pre-trained Convolutional Neural Networks (CNN) for the early detection of two common grapevine diseases: peronospora and o´ıdio. These diseases present similar symptoms and are of great viticultural importance. Our objective is to train a CNN using transfer learning techniques to accurately detect the presence of early symptoms of the diseases under study. To achieve that, we’ll design a pipeline that starts with data acquisition in the field and finalizes with the early disease identification, including class definition, labeling, image preprocessing and training process of the CNN, employing edge computing-based service computing paradigm to overcome some inherent problems of traditional mobile cloud computing paradigm. Facultad de Informática Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 41-45
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Deep Learning
Convolutional Neural Networks
Object Detection
Edge Computing
Inclusive Inteligent Systems
spellingShingle Ciencias Informáticas
Deep Learning
Convolutional Neural Networks
Object Detection
Edge Computing
Inclusive Inteligent Systems
Rios, Cristian Emmanuel
Estrebou, César Armando
Frati, Fernando Emmanuel
Early detection of grapevine diseases using pre-trained Convolutional Neural Networks
topic_facet Ciencias Informáticas
Deep Learning
Convolutional Neural Networks
Object Detection
Edge Computing
Inclusive Inteligent Systems
description This paper proposes to apply pre-trained Convolutional Neural Networks (CNN) for the early detection of two common grapevine diseases: peronospora and o´ıdio. These diseases present similar symptoms and are of great viticultural importance. Our objective is to train a CNN using transfer learning techniques to accurately detect the presence of early symptoms of the diseases under study. To achieve that, we’ll design a pipeline that starts with data acquisition in the field and finalizes with the early disease identification, including class definition, labeling, image preprocessing and training process of the CNN, employing edge computing-based service computing paradigm to overcome some inherent problems of traditional mobile cloud computing paradigm.
format Objeto de conferencia
Objeto de conferencia
author Rios, Cristian Emmanuel
Estrebou, César Armando
Frati, Fernando Emmanuel
author_facet Rios, Cristian Emmanuel
Estrebou, César Armando
Frati, Fernando Emmanuel
author_sort Rios, Cristian Emmanuel
title Early detection of grapevine diseases using pre-trained Convolutional Neural Networks
title_short Early detection of grapevine diseases using pre-trained Convolutional Neural Networks
title_full Early detection of grapevine diseases using pre-trained Convolutional Neural Networks
title_fullStr Early detection of grapevine diseases using pre-trained Convolutional Neural Networks
title_full_unstemmed Early detection of grapevine diseases using pre-trained Convolutional Neural Networks
title_sort early detection of grapevine diseases using pre-trained convolutional neural networks
publishDate 2023
url http://sedici.unlp.edu.ar/handle/10915/155434
work_keys_str_mv AT rioscristianemmanuel earlydetectionofgrapevinediseasesusingpretrainedconvolutionalneuralnetworks
AT estreboucesararmando earlydetectionofgrapevinediseasesusingpretrainedconvolutionalneuralnetworks
AT fratifernandoemmanuel earlydetectionofgrapevinediseasesusingpretrainedconvolutionalneuralnetworks
_version_ 1771439086888812544

Ejemplares similares