Publication: Enhancement of plant leaf disease classification based on snapshot ensemble convolutional neural network
Submitted Date
Received Date
Accepted Date
Issued Date
2021
Copyright Date
Announcement No.
Application No.
Patent No.
Valid Date
Resource Type
Edition
Resource Version
Language
en
File Type
No. of Pages/File Size
ISBN
ISSN
eISSN
Scopus ID
WOS ID
Pubmed ID
arXiv ID
item.page.harrt.identifier.callno
Other identifier(s)
Journal Title
ICIC Express Letters
Volume
15
Issue
6
Edition
Start Page
669
End Page
680
Access Rights
Access Status
Rights
Rights Holder(s)
Physical Location
Bibliographic Citation
Research Projects
Organizational Units
Authors
Journal Issue
Title
Enhancement of plant leaf disease classification based on snapshot ensemble convolutional neural network
Alternative Title(s)
Author(s)
Author's E-mail
Editor(s)
Editor’s Affiliation
Corresponding person(s)
Creator(s)
Compiler
Advisor(s)
Illustrator(s)
Applicant(s)
Inventor(s)
Issuer
Assignee
Other Contributor(s)
Series
Has Part
Abstract
Plant diseases are one of the most serious issues that can decrease the value and volume of plant goods. It is time-consuming for farmers to discover and identify the disease by observing the leaves of plants; even with specialists scientists and laboratory processes. This study proposed the deep learning approach to address the real-world problems that are contained in the PlantDoc dataset. The deep learning method aims to classify plant leaf disease images from the PlantDoc dataset. First; four state-of-the-art convolutional neural networks (CNNs): VGG16; MobileNetV2; InceptionResNetV2; and DenseNet201; were proposed to enhance the plant leaf disease classification performance. As a result; for the baseline CNN model; DenseNet201 showed better performance with an accuracy of 67.18%; while the second-best CNN model was the InceptionResNetV2 with an accuracy of 61.75%. In addition; the data augmentation techniques (rotation; zoom; brightness; cutout; and mixup) were combined in the training process. The InceptionRes-NetV2 when combined with the rotation technique obtained an accuracy of 66.02% and outperformed all other CNNs. Importantly; based on our experimental results; the data augmentation techniques with brightness; cutout; and mixup were less satisfactory on the PlantDoc dataset. Second; we proposed the snapshot ensemble to improve the performance of the CNN models. We evaluated the classification performance by applying the snapshot ensemble with 4 and 5 cosine annealing cycles and optimized the learning rate using a stochastic gradient descent algorithm. We also examined the snapshot ensemble with the weighted and unweighted ensemble methods. The experimental results showed that the DenseNet201 when training with the snapshot ensemble method (4-cycle) obtained the accuracy of 69.51%.