Data Augmentation Method for Plant Leaf Disease Recognition
Recently, several plant pathogens have become more active due to temperature increases arising from climate change, which has caused damage to various crops. If climate change continues, it will likely be very difficult to maintain current crop production, and the problem of a shortage of expert man...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/3/1465 |
_version_ | 1797625211597619200 |
---|---|
author | Byeongjun Min Taehyun Kim Dongil Shin Dongkyoo Shin |
author_facet | Byeongjun Min Taehyun Kim Dongil Shin Dongkyoo Shin |
author_sort | Byeongjun Min |
collection | DOAJ |
description | Recently, several plant pathogens have become more active due to temperature increases arising from climate change, which has caused damage to various crops. If climate change continues, it will likely be very difficult to maintain current crop production, and the problem of a shortage of expert manpower is also deepening. Fortunately, research on various early diagnosis systems based on deep learning is actively underway to solve these problems, but the problem of lack of diversity in some hard-to-collect disease samples remains. This imbalanced data increases the bias of machine learning models, causing overfitting problems. In this paper, we propose a data augmentation method based on an image-to-image translation model to solve the bias problem by supplementing these insufficient diseased leaf images. The proposed augmentation method performs translation between healthy and diseased leaf images and utilizes attention mechanisms to create images that reflect more evident disease textures. Through these improvements, we generated a more plausible diseased leaf image compared to existing methods and conducted an experiment to verify whether this data augmentation method could further improve the performance of a classification model for early diagnosis of plants. In the experiment, the PlantVillage dataset was used, and the extended dataset was built using the generated images and original images, and the performance of the classification models was evaluated through the test set. |
first_indexed | 2024-03-11T09:53:21Z |
format | Article |
id | doaj.art-c67a50d224b34f5596a7c89551cb5d65 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-11T09:53:21Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-c67a50d224b34f5596a7c89551cb5d652023-11-16T16:05:49ZengMDPI AGApplied Sciences2076-34172023-01-01133146510.3390/app13031465Data Augmentation Method for Plant Leaf Disease RecognitionByeongjun Min0Taehyun Kim1Dongil Shin2Dongkyoo Shin3Department of Computer Engineering, Sejong University, Seoul 05006, Republic of KoreaDepartment of Agriculture Engineering, National Institute of Agricultural Sciences, Jeonju 63240, Republic of KoreaDepartment of Computer Engineering, Sejong University, Seoul 05006, Republic of KoreaDepartment of Computer Engineering, Sejong University, Seoul 05006, Republic of KoreaRecently, several plant pathogens have become more active due to temperature increases arising from climate change, which has caused damage to various crops. If climate change continues, it will likely be very difficult to maintain current crop production, and the problem of a shortage of expert manpower is also deepening. Fortunately, research on various early diagnosis systems based on deep learning is actively underway to solve these problems, but the problem of lack of diversity in some hard-to-collect disease samples remains. This imbalanced data increases the bias of machine learning models, causing overfitting problems. In this paper, we propose a data augmentation method based on an image-to-image translation model to solve the bias problem by supplementing these insufficient diseased leaf images. The proposed augmentation method performs translation between healthy and diseased leaf images and utilizes attention mechanisms to create images that reflect more evident disease textures. Through these improvements, we generated a more plausible diseased leaf image compared to existing methods and conducted an experiment to verify whether this data augmentation method could further improve the performance of a classification model for early diagnosis of plants. In the experiment, the PlantVillage dataset was used, and the extended dataset was built using the generated images and original images, and the performance of the classification models was evaluated through the test set.https://www.mdpi.com/2076-3417/13/3/1465plant disease recognitiondata augmentationimbalanced datasetconvolutional attention |
spellingShingle | Byeongjun Min Taehyun Kim Dongil Shin Dongkyoo Shin Data Augmentation Method for Plant Leaf Disease Recognition Applied Sciences plant disease recognition data augmentation imbalanced dataset convolutional attention |
title | Data Augmentation Method for Plant Leaf Disease Recognition |
title_full | Data Augmentation Method for Plant Leaf Disease Recognition |
title_fullStr | Data Augmentation Method for Plant Leaf Disease Recognition |
title_full_unstemmed | Data Augmentation Method for Plant Leaf Disease Recognition |
title_short | Data Augmentation Method for Plant Leaf Disease Recognition |
title_sort | data augmentation method for plant leaf disease recognition |
topic | plant disease recognition data augmentation imbalanced dataset convolutional attention |
url | https://www.mdpi.com/2076-3417/13/3/1465 |
work_keys_str_mv | AT byeongjunmin dataaugmentationmethodforplantleafdiseaserecognition AT taehyunkim dataaugmentationmethodforplantleafdiseaserecognition AT dongilshin dataaugmentationmethodforplantleafdiseaserecognition AT dongkyooshin dataaugmentationmethodforplantleafdiseaserecognition |