Disease detection in tomato leaves via CNN with lightweight architectures implemented in Raspberry Pi 4

•Deep transfer learning for disease detection in tomato leaves.•Evaluation and analysis from CNN models to select more suitable for a specific task.•Raspberry Pi 4 implementation for real-field operations.•GUI designed for easy usage. Deep learning has made essential contributions to classification...

Full description

Saved in:
Bibliographic Details
Published in:Computers and electronics in agriculture Vol. 181; p. 105951
Main Authors: Gonzalez-Huitron, Victor, León-Borges, José A., Rodriguez-Mata, A.E., Amabilis-Sosa, Leonel Ernesto, Ramírez-Pereda, Blenda, Rodriguez, Hector
Format: Journal Article
Language:English
Published: Amsterdam Elsevier B.V 01.02.2021
Elsevier BV
Subjects:
agriculture
Algorithms
Artificial neural networks
Classification
Color imagery
Convolution
data collection
Deep learning
disease detection
Electronic devices
electronics
Evaluation
Graphical user interface
Image processing
Machine learning
Plant disease classification
Precision agriculture
raspberries
Tomatoes
user interface
Deep learning
Precision agriculture
Plant disease classification
Image processing
ISSN:0168-1699, 1872-7107
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Deep transfer learning for disease detection in tomato leaves.•Evaluation and analysis from CNN models to select more suitable for a specific task.•Raspberry Pi 4 implementation for real-field operations.•GUI designed for easy usage. Deep learning has made essential contributions to classification and detection tasks applied to precision agriculture; however, it is vitally important to move towards an adoption of these techniques and algorithms through low-cost and low-consumption devices for daily use in crop fields. In this paper, we present the training and evaluation of four recent Convolutional Neural Networks models for the classification of diseases in tomato leaves. A subset of the Plantvillage dataset consisting of 18,160 RGB images has been divided into ten classes for transfer learning. The selected models have depthwise separable convolution architecture for application in low-power devices. Evaluation and analysis quantitatively and qualitatively is performed via quality metrics and saliency maps. Finally, an implementation on the Raspberry Pi 4 microcomputer with a graphical user interface is developed.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0168-1699
1872-7107
DOI:10.1016/j.compag.2020.105951