Plant Disease Detection Using Deep Convolutional Neural Network
In this research, we proposed a novel 14-layered deep convolutional neural network (14-DCNN) to detect plant leaf diseases using leaf images. A new dataset was created using various open datasets. Data augmentation techniques were used to balance the individual class sizes of the dataset. Three imag...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/14/6982 |
| _version_ | 1797407628449546240 |
|---|---|
| author | J. Arun Pandian V. Dhilip Kumar Oana Geman Mihaela Hnatiuc Muhammad Arif K. Kanchanadevi |
| author_facet | J. Arun Pandian V. Dhilip Kumar Oana Geman Mihaela Hnatiuc Muhammad Arif K. Kanchanadevi |
| author_sort | J. Arun Pandian |
| collection | DOAJ |
| description | In this research, we proposed a novel 14-layered deep convolutional neural network (14-DCNN) to detect plant leaf diseases using leaf images. A new dataset was created using various open datasets. Data augmentation techniques were used to balance the individual class sizes of the dataset. Three image augmentation techniques were used: basic image manipulation (BIM), deep convolutional generative adversarial network (DCGAN) and neural style transfer (NST). The dataset consists of 147,500 images of 58 different healthy and diseased plant leaf classes and one no-leaf class. The proposed DCNN model was trained in the multi-graphics processing units (MGPUs) environment for 1000 epochs. The random search with the coarse-to-fine searching technique was used to select the most suitable hyperparameter values to improve the training performance of the proposed DCNN model. On the 8850 test images, the proposed DCNN model achieved 99.9655% overall classification accuracy, 99.7999% weighted average precision, 99.7966% weighted average recall, and 99.7968% weighted average F1 score. Additionally, the overall performance of the proposed DCNN model was better than the existing transfer learning approaches. |
| first_indexed | 2024-03-09T03:45:13Z |
| format | Article |
| id | doaj.art-447404f02dea49aa99136332453ca533 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T03:45:13Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-447404f02dea49aa99136332453ca5332023-12-03T14:35:41ZengMDPI AGApplied Sciences2076-34172022-07-011214698210.3390/app12146982Plant Disease Detection Using Deep Convolutional Neural NetworkJ. Arun Pandian0V. Dhilip Kumar1Oana Geman2Mihaela Hnatiuc3Muhammad Arif4K. Kanchanadevi5Computer Science & Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai 600062, IndiaComputer Science & Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai 600062, IndiaNeuroaesthetic Lab, Bioinstrumentation and Medical Tecniques Group, Faculty of Electrical Engineering and Computer Science, Stefan cel Mare University of Suceava, 720229 Suceava, RomaniaElectromechanical Faculty, Department of Telecomunication and Electronics, Maritime University of Constanta, 900663 Constanta, RomaniaDepartment of Computer Science and Information Technology, University of Lahore, Lahore 54590, PakistanComputer Science & Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai 600062, IndiaIn this research, we proposed a novel 14-layered deep convolutional neural network (14-DCNN) to detect plant leaf diseases using leaf images. A new dataset was created using various open datasets. Data augmentation techniques were used to balance the individual class sizes of the dataset. Three image augmentation techniques were used: basic image manipulation (BIM), deep convolutional generative adversarial network (DCGAN) and neural style transfer (NST). The dataset consists of 147,500 images of 58 different healthy and diseased plant leaf classes and one no-leaf class. The proposed DCNN model was trained in the multi-graphics processing units (MGPUs) environment for 1000 epochs. The random search with the coarse-to-fine searching technique was used to select the most suitable hyperparameter values to improve the training performance of the proposed DCNN model. On the 8850 test images, the proposed DCNN model achieved 99.9655% overall classification accuracy, 99.7999% weighted average precision, 99.7966% weighted average recall, and 99.7968% weighted average F1 score. Additionally, the overall performance of the proposed DCNN model was better than the existing transfer learning approaches.https://www.mdpi.com/2076-3417/12/14/6982deep convolutional neural networksgenerative adversarial networkbasic image manipulationrandom searchhyperparameter optimizationneural style transfer |
| spellingShingle | J. Arun Pandian V. Dhilip Kumar Oana Geman Mihaela Hnatiuc Muhammad Arif K. Kanchanadevi Plant Disease Detection Using Deep Convolutional Neural Network Applied Sciences deep convolutional neural networks generative adversarial network basic image manipulation random search hyperparameter optimization neural style transfer |
| title | Plant Disease Detection Using Deep Convolutional Neural Network |
| title_full | Plant Disease Detection Using Deep Convolutional Neural Network |
| title_fullStr | Plant Disease Detection Using Deep Convolutional Neural Network |
| title_full_unstemmed | Plant Disease Detection Using Deep Convolutional Neural Network |
| title_short | Plant Disease Detection Using Deep Convolutional Neural Network |
| title_sort | plant disease detection using deep convolutional neural network |
| topic | deep convolutional neural networks generative adversarial network basic image manipulation random search hyperparameter optimization neural style transfer |
| url | https://www.mdpi.com/2076-3417/12/14/6982 |
| work_keys_str_mv | AT jarunpandian plantdiseasedetectionusingdeepconvolutionalneuralnetwork AT vdhilipkumar plantdiseasedetectionusingdeepconvolutionalneuralnetwork AT oanageman plantdiseasedetectionusingdeepconvolutionalneuralnetwork AT mihaelahnatiuc plantdiseasedetectionusingdeepconvolutionalneuralnetwork AT muhammadarif plantdiseasedetectionusingdeepconvolutionalneuralnetwork AT kkanchanadevi plantdiseasedetectionusingdeepconvolutionalneuralnetwork |