Classification of Plant Leaf Disease Recognition Based on Self-Supervised Learning
Accurate identification of plant diseases is a critical task in agricultural production. The existing deep learning crop disease recognition methods require a large number of labeled images for training, limiting the implementation of large-scale detection. To overcome this limitation, this study ex...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/14/3/500 |
| _version_ | 1797242418924355584 |
|---|---|
| author | Yuzhi Wang Yunzhen Yin Yaoyu Li Tengteng Qu Zhaodong Guo Mingkang Peng Shujie Jia Qiang Wang Wuping Zhang Fuzhong Li |
| author_facet | Yuzhi Wang Yunzhen Yin Yaoyu Li Tengteng Qu Zhaodong Guo Mingkang Peng Shujie Jia Qiang Wang Wuping Zhang Fuzhong Li |
| author_sort | Yuzhi Wang |
| collection | DOAJ |
| description | Accurate identification of plant diseases is a critical task in agricultural production. The existing deep learning crop disease recognition methods require a large number of labeled images for training, limiting the implementation of large-scale detection. To overcome this limitation, this study explores the application of self-supervised learning (SSL) in plant disease recognition. We propose a new model that combines a masked autoencoder (MAE) and a convolutional block attention module (CBAM) to alleviate the harsh requirements of large amounts of labeled data. The performance of the model was validated on the CCMT dataset and our collected dataset. The results show that the improved model achieves an accuracy of 95.35% and 99.61%, recall of 96.2% and 98.51%, and F1 values of 95.52% and 98.62% on the CCMT dataset and our collected dataset, respectively. Compared with ResNet50, ViT, and MAE, the accuracies on the CCMT dataset improved by 1.2%, 0.7%, and 0.8%, respectively, and the accuracy of our collected dataset improved by 1.3%, 1.6%, and 0.6%, respectively. Through experiments on 21 leaf diseases (early blight, late blight, leaf blight, leaf spot, etc.) of five crops, namely, potato, maize, tomato, cashew, and cassava, our model achieved accurate and rapid detection of plant disease categories. This study provides a reference for research work and engineering applications in crop disease detection. |
| first_indexed | 2024-04-24T18:38:55Z |
| format | Article |
| id | doaj.art-842d70f0bad34b7195060d073acbbc54 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-04-24T18:38:55Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-842d70f0bad34b7195060d073acbbc542024-03-27T13:16:43ZengMDPI AGAgronomy2073-43952024-02-0114350010.3390/agronomy14030500Classification of Plant Leaf Disease Recognition Based on Self-Supervised LearningYuzhi Wang0Yunzhen Yin1Yaoyu Li2Tengteng Qu3Zhaodong Guo4Mingkang Peng5Shujie Jia6Qiang Wang7Wuping Zhang8Fuzhong Li9College of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaCollege of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaCollege of Agricultural Engineering, Shanxi Agricultural University, Jinzhong 030801, ChinaCollege of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaCollege of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaCollege of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaCollege of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaCollege of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaCollege of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaCollege of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaAccurate identification of plant diseases is a critical task in agricultural production. The existing deep learning crop disease recognition methods require a large number of labeled images for training, limiting the implementation of large-scale detection. To overcome this limitation, this study explores the application of self-supervised learning (SSL) in plant disease recognition. We propose a new model that combines a masked autoencoder (MAE) and a convolutional block attention module (CBAM) to alleviate the harsh requirements of large amounts of labeled data. The performance of the model was validated on the CCMT dataset and our collected dataset. The results show that the improved model achieves an accuracy of 95.35% and 99.61%, recall of 96.2% and 98.51%, and F1 values of 95.52% and 98.62% on the CCMT dataset and our collected dataset, respectively. Compared with ResNet50, ViT, and MAE, the accuracies on the CCMT dataset improved by 1.2%, 0.7%, and 0.8%, respectively, and the accuracy of our collected dataset improved by 1.3%, 1.6%, and 0.6%, respectively. Through experiments on 21 leaf diseases (early blight, late blight, leaf blight, leaf spot, etc.) of five crops, namely, potato, maize, tomato, cashew, and cassava, our model achieved accurate and rapid detection of plant disease categories. This study provides a reference for research work and engineering applications in crop disease detection.https://www.mdpi.com/2073-4395/14/3/500plant disease recognitionself-supervised learningdeep learningmasked autoencoderattention mechanism |
| spellingShingle | Yuzhi Wang Yunzhen Yin Yaoyu Li Tengteng Qu Zhaodong Guo Mingkang Peng Shujie Jia Qiang Wang Wuping Zhang Fuzhong Li Classification of Plant Leaf Disease Recognition Based on Self-Supervised Learning Agronomy plant disease recognition self-supervised learning deep learning masked autoencoder attention mechanism |
| title | Classification of Plant Leaf Disease Recognition Based on Self-Supervised Learning |
| title_full | Classification of Plant Leaf Disease Recognition Based on Self-Supervised Learning |
| title_fullStr | Classification of Plant Leaf Disease Recognition Based on Self-Supervised Learning |
| title_full_unstemmed | Classification of Plant Leaf Disease Recognition Based on Self-Supervised Learning |
| title_short | Classification of Plant Leaf Disease Recognition Based on Self-Supervised Learning |
| title_sort | classification of plant leaf disease recognition based on self supervised learning |
| topic | plant disease recognition self-supervised learning deep learning masked autoencoder attention mechanism |
| url | https://www.mdpi.com/2073-4395/14/3/500 |
| work_keys_str_mv | AT yuzhiwang classificationofplantleafdiseaserecognitionbasedonselfsupervisedlearning AT yunzhenyin classificationofplantleafdiseaserecognitionbasedonselfsupervisedlearning AT yaoyuli classificationofplantleafdiseaserecognitionbasedonselfsupervisedlearning AT tengtengqu classificationofplantleafdiseaserecognitionbasedonselfsupervisedlearning AT zhaodongguo classificationofplantleafdiseaserecognitionbasedonselfsupervisedlearning AT mingkangpeng classificationofplantleafdiseaserecognitionbasedonselfsupervisedlearning AT shujiejia classificationofplantleafdiseaserecognitionbasedonselfsupervisedlearning AT qiangwang classificationofplantleafdiseaserecognitionbasedonselfsupervisedlearning AT wupingzhang classificationofplantleafdiseaserecognitionbasedonselfsupervisedlearning AT fuzhongli classificationofplantleafdiseaserecognitionbasedonselfsupervisedlearning |