A Five Convolutional Layer Deep Convolutional Neural Network for Plant Leaf Disease Detection
In this research, we proposed a Deep Convolutional Neural Network (DCNN) model for image-based plant leaf disease identification using data augmentation and hyperparameter optimization techniques. The DCNN model was trained on an augmented dataset of over 240,000 images of different healthy and dise...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/11/8/1266 |
_version_ | 1797434834180636672 |
---|---|
author | J. Arun Pandian K. Kanchanadevi V. Dhilip Kumar Elżbieta Jasińska Radomír Goňo Zbigniew Leonowicz Michał Jasiński |
author_facet | J. Arun Pandian K. Kanchanadevi V. Dhilip Kumar Elżbieta Jasińska Radomír Goňo Zbigniew Leonowicz Michał Jasiński |
author_sort | J. Arun Pandian |
collection | DOAJ |
description | In this research, we proposed a Deep Convolutional Neural Network (DCNN) model for image-based plant leaf disease identification using data augmentation and hyperparameter optimization techniques. The DCNN model was trained on an augmented dataset of over 240,000 images of different healthy and diseased plant leaves and backgrounds. Five image augmentation techniques were used: Generative Adversarial Network, Neural Style Transfer, Principal Component Analysis, Color Augmentation, and Position Augmentation. The random search technique was used to optimize the hyperparameters of the proposed DCNN model. This research shows the significance of choosing a suitable number of layers and filters in DCNN development. Moreover, the experimental outcomes illustrate the importance of data augmentation techniques and hyperparameter optimization techniques. The performance of the proposed DCNN was calculated using different performance metrics such as classification accuracy, precision, recall, and F1-Score. The experimental results show that the proposed DCNN model achieves an average classification accuracy of 98.41% on the test dataset. Moreover, the overall performance of the proposed DCNN model was better than that of advanced transfer learning and machine learning techniques. The proposed DCNN model is useful in the identification of plant leaf diseases. |
first_indexed | 2024-03-09T10:38:37Z |
format | Article |
id | doaj.art-544f4aa75e824f308426801ad33ed71e |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-09T10:38:37Z |
publishDate | 2022-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-544f4aa75e824f308426801ad33ed71e2023-12-01T20:47:23ZengMDPI AGElectronics2079-92922022-04-01118126610.3390/electronics11081266A Five Convolutional Layer Deep Convolutional Neural Network for Plant Leaf Disease DetectionJ. Arun Pandian0K. Kanchanadevi1V. Dhilip Kumar2Elżbieta Jasińska3Radomír Goňo4Zbigniew Leonowicz5Michał Jasiński6Computer 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, IndiaComputer Science & Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai 600062, IndiaDepartment of Operations Research and Business Intelligence, Wrocław University of Science and Technology, 50-370 Wroclaw, PolandDepartment of Electrical Power Engineering, Faculty of Electrical Engineering and Computer Science, VSB—Technical University of Ostrava, 708 00 Ostrava, Czech RepublicFaculty of Electrical Engineering, Wroclaw University of Science and Technology, 50-370 Wroclaw, PolandFaculty of Electrical Engineering, Wroclaw University of Science and Technology, 50-370 Wroclaw, PolandIn this research, we proposed a Deep Convolutional Neural Network (DCNN) model for image-based plant leaf disease identification using data augmentation and hyperparameter optimization techniques. The DCNN model was trained on an augmented dataset of over 240,000 images of different healthy and diseased plant leaves and backgrounds. Five image augmentation techniques were used: Generative Adversarial Network, Neural Style Transfer, Principal Component Analysis, Color Augmentation, and Position Augmentation. The random search technique was used to optimize the hyperparameters of the proposed DCNN model. This research shows the significance of choosing a suitable number of layers and filters in DCNN development. Moreover, the experimental outcomes illustrate the importance of data augmentation techniques and hyperparameter optimization techniques. The performance of the proposed DCNN was calculated using different performance metrics such as classification accuracy, precision, recall, and F1-Score. The experimental results show that the proposed DCNN model achieves an average classification accuracy of 98.41% on the test dataset. Moreover, the overall performance of the proposed DCNN model was better than that of advanced transfer learning and machine learning techniques. The proposed DCNN model is useful in the identification of plant leaf diseases.https://www.mdpi.com/2079-9292/11/8/1266data augmentationdeep convolutional neural networksgenerative adversarial networkhyperparameters optimizationneural style transferprincipal component analysis |
spellingShingle | J. Arun Pandian K. Kanchanadevi V. Dhilip Kumar Elżbieta Jasińska Radomír Goňo Zbigniew Leonowicz Michał Jasiński A Five Convolutional Layer Deep Convolutional Neural Network for Plant Leaf Disease Detection Electronics data augmentation deep convolutional neural networks generative adversarial network hyperparameters optimization neural style transfer principal component analysis |
title | A Five Convolutional Layer Deep Convolutional Neural Network for Plant Leaf Disease Detection |
title_full | A Five Convolutional Layer Deep Convolutional Neural Network for Plant Leaf Disease Detection |
title_fullStr | A Five Convolutional Layer Deep Convolutional Neural Network for Plant Leaf Disease Detection |
title_full_unstemmed | A Five Convolutional Layer Deep Convolutional Neural Network for Plant Leaf Disease Detection |
title_short | A Five Convolutional Layer Deep Convolutional Neural Network for Plant Leaf Disease Detection |
title_sort | five convolutional layer deep convolutional neural network for plant leaf disease detection |
topic | data augmentation deep convolutional neural networks generative adversarial network hyperparameters optimization neural style transfer principal component analysis |
url | https://www.mdpi.com/2079-9292/11/8/1266 |
work_keys_str_mv | AT jarunpandian afiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT kkanchanadevi afiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT vdhilipkumar afiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT elzbietajasinska afiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT radomirgono afiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT zbigniewleonowicz afiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT michałjasinski afiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT jarunpandian fiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT kkanchanadevi fiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT vdhilipkumar fiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT elzbietajasinska fiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT radomirgono fiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT zbigniewleonowicz fiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection AT michałjasinski fiveconvolutionallayerdeepconvolutionalneuralnetworkforplantleafdiseasedetection |