Deep learning model for detection and classification of banana diseases based on leaf images

Fungal diseases are among the main reasons for low productivity in banana farming. Early detection of fungal diseases is essential. One possible approach is using machine vision. Due to its high accuracy, deep learning is the most widely used algorithm in machine vision for many solutions. Its abili...

Full description

Saved in:
Bibliographic Details
Published in:IOP conference series. Earth and environmental science 2024-06, Vol.1359 (1), p.12010
Main Authors: Nassor, S, Mushthofa, M, Priandana, K
Format: Article
Language:English
Subjects:
Abnormalities
Accuracy
Agricultural equipment
Algorithms
Black Sigatoka
Classification
Deep learning
Fruits
Fungal diseases
Fungi
Learning algorithms
Leaves
Lightweight
Machine learning
Machine vision
Medical imaging
Training
Vision systems
Weight reduction
Wilt
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fungal diseases are among the main reasons for low productivity in banana farming. Early detection of fungal diseases is essential. One possible approach is using machine vision. Due to its high accuracy, deep learning is the most widely used algorithm in machine vision for many solutions. Its ability to model the data into multiple levels of abstraction makes it suitable for many agricultural solutions. However, deep learning requires a high computational resource, challenging many agricultural solutions implemented on low-computing devices. This study proposes lightweight deep-learning algorithms for detecting and classifying banana diseases based on leaf images. The study used a dataset of images representing three classes: black Sigatoka disease, fusarium wilt race 1 disease, and healthy tree. The algorithms used are mobileNetv2, mobileNetv3-small, shuffleNetv2, and squeezeNet. The results showed that squeezeNet outperforms all other models with 97.12% accuracy, 97.14% precision, 97.1% recall, and 97.12% f1-score. MobileNetv3-small results in the heaviest model, which is 14 MB, but it has the shortest training time of 2.465 minutes. MobileNetv2 results in the lightest model, 2.51 MB, while squeezeNet has the longest training time, 14.76 minutes. Overall, the lightweight deep learning algorithms performed well, and this method can be used for other banana diseases and abnormalities.
ISSN:1755-1307
1755-1315
DOI:10.1088/1755-1315/1359/1/012010