Multispectral Plant Disease Detection with Vision Transformer–Convolutional Neural Network Hybrid Approaches
Plant diseases pose a critical threat to global agricultural productivity, demanding timely detection for effective crop yield management. Traditional methods for disease identification are laborious and require specialised expertise. Leveraging cutting-edge deep learning algorithms, this study expl...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/20/8531 |
| _version_ | 1797572279894278144 |
|---|---|
| author | Malithi De Silva Dane Brown |
| author_facet | Malithi De Silva Dane Brown |
| author_sort | Malithi De Silva |
| collection | DOAJ |
| description | Plant diseases pose a critical threat to global agricultural productivity, demanding timely detection for effective crop yield management. Traditional methods for disease identification are laborious and require specialised expertise. Leveraging cutting-edge deep learning algorithms, this study explores innovative approaches to plant disease identification, combining Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to enhance accuracy. A multispectral dataset was meticulously collected to facilitate this research using six 50 mm filter filters, covering both the visible and several near-infrared (NIR) wavelengths. Among the models employed, ViT-B16 notably achieved the highest test accuracy, precision, recall, and F1 score across all filters, with averages of 83.3%, 90.1%, 90.75%, and 89.5%, respectively. Furthermore, a comparative analysis highlights the pivotal role of balanced datasets in selecting the appropriate wavelength and deep learning model for robust disease identification. These findings promise to advance crop disease management in real-world agricultural applications and contribute to global food security. The study underscores the significance of machine learning in transforming plant disease diagnostics and encourages further research in this field. |
| first_indexed | 2024-03-10T20:54:59Z |
| format | Article |
| id | doaj.art-b34177132d5947bdb1910cfedfa5596d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:54:59Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b34177132d5947bdb1910cfedfa5596d2023-11-19T18:04:19ZengMDPI AGSensors1424-82202023-10-012320853110.3390/s23208531Multispectral Plant Disease Detection with Vision Transformer–Convolutional Neural Network Hybrid ApproachesMalithi De Silva0Dane Brown1The Department of Computer Science, Rhodes University, Hamilton Building, Prince Alfred Street, Grahamstown 6139, South AfricaThe Department of Computer Science, Rhodes University, Hamilton Building, Prince Alfred Street, Grahamstown 6139, South AfricaPlant diseases pose a critical threat to global agricultural productivity, demanding timely detection for effective crop yield management. Traditional methods for disease identification are laborious and require specialised expertise. Leveraging cutting-edge deep learning algorithms, this study explores innovative approaches to plant disease identification, combining Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to enhance accuracy. A multispectral dataset was meticulously collected to facilitate this research using six 50 mm filter filters, covering both the visible and several near-infrared (NIR) wavelengths. Among the models employed, ViT-B16 notably achieved the highest test accuracy, precision, recall, and F1 score across all filters, with averages of 83.3%, 90.1%, 90.75%, and 89.5%, respectively. Furthermore, a comparative analysis highlights the pivotal role of balanced datasets in selecting the appropriate wavelength and deep learning model for robust disease identification. These findings promise to advance crop disease management in real-world agricultural applications and contribute to global food security. The study underscores the significance of machine learning in transforming plant disease diagnostics and encourages further research in this field.https://www.mdpi.com/1424-8220/23/20/8531plant disease identificationdeep-learningCNNViTmultispectral imagesNIR |
| spellingShingle | Malithi De Silva Dane Brown Multispectral Plant Disease Detection with Vision Transformer–Convolutional Neural Network Hybrid Approaches Sensors plant disease identification deep-learning CNN ViT multispectral images NIR |
| title | Multispectral Plant Disease Detection with Vision Transformer–Convolutional Neural Network Hybrid Approaches |
| title_full | Multispectral Plant Disease Detection with Vision Transformer–Convolutional Neural Network Hybrid Approaches |
| title_fullStr | Multispectral Plant Disease Detection with Vision Transformer–Convolutional Neural Network Hybrid Approaches |
| title_full_unstemmed | Multispectral Plant Disease Detection with Vision Transformer–Convolutional Neural Network Hybrid Approaches |
| title_short | Multispectral Plant Disease Detection with Vision Transformer–Convolutional Neural Network Hybrid Approaches |
| title_sort | multispectral plant disease detection with vision transformer convolutional neural network hybrid approaches |
| topic | plant disease identification deep-learning CNN ViT multispectral images NIR |
| url | https://www.mdpi.com/1424-8220/23/20/8531 |
| work_keys_str_mv | AT malithidesilva multispectralplantdiseasedetectionwithvisiontransformerconvolutionalneuralnetworkhybridapproaches AT danebrown multispectralplantdiseasedetectionwithvisiontransformerconvolutionalneuralnetworkhybridapproaches |