Optimized Crop Disease Identification in Bangladesh: A Deep Learning and SVM Hybrid Model for Rice, Potato, and Corn
Abstract
:1. Introduction
2. Methodology
2.1. Dataset Preparation
2.1.1. Data Preprocessing
2.1.2. Image Resizing
2.1.3. Normalization
2.1.4. Data Augmentation
2.1.5. Train-Test Split
2.2. Model Selection
2.2.1. EfficientNetB0 for Feature Extraction
2.2.2. SVM for Classification
2.2.3. Hybrid Model
2.2.4. EfficientNet Architecture
2.2.5. Transfer Learning
2.2.6. Feature Extraction Process
- Input images: At the outset, our crop disease detection system receives input images depicting various crops, such as corn, rice, or potatoes [32]. These images serve as the raw data input into the EfficientNetB0 model, capturing visual information about the crops’ appearance and condition.
- Propagating through layers: Once the input images are fed into the model, they propagate through the layers of the EfficientNetB0 architecture. The model learns from its errors through backpropagation.
- Extraction of abstract features: As the images traverse through the network, the successive layers extract increasingly abstract and complex features [33,34]. Initially, lower layers may detect simple patterns like edges and textures, while deeper layers capture more sophisticated structures and arrangements specific to crop diseases.
- Aggregation and processing: The extracted features from different layers are aggregated and processed further as they progress through the network [35,36]. Through the process of feature fusion and refinement, the model learns to combine and manipulate the extracted features to enhance their representational power.
2.2.7. Model Training
3. Results and Discussion
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Robinson, A. Late Blight in Potato. NDSU Agriculture and Extension, 5 May 2017. Available online: https://www.ndsu.edu/agriculture/extension/publications/late-blight-potato (accessed on 15 March 2024).
- Andrivon, D. Biology, ecology, and epidemiology of the potato late blight pathogen Phytophthora infestans in soil. Phytopathology 1995, 85, 1053–1056. [Google Scholar] [CrossRef]
- Shi, X.; Yang, J. Hybrid system of convolutional neural networks and SVM for multi-class MIEEG classification. In Proceedings of the 2019 IEEE 11th International Conference on Advanced Infocomm Technology (ICAIT), Jinan, China, 18–20 October 2019; pp. 137–141. [Google Scholar]
- Bansal, P.; Kumar, R.; Kumar, S. Disease detection in apple leaves using deep convolutional neural network. Agriculture 2021, 11, 617. [Google Scholar] [CrossRef]
- Afzaal, H.; Farooque, A.A.; Schumann, A.W.; Hussain, N.; McKenzie-Gopsill, A.; Esau, T.; Abbas, F.; Acharya, B. Detection of a potato disease (early blight) using artificial intelligence. Remote Sens. 2021, 13, 411. [Google Scholar] [CrossRef]
- Mia, M.J.; Maria, S.K.; Taki, S.S.; Biswas, A.A. Cucumber disease recognition using machine learning and transfer learning. Bull. Electr. Eng. Inform. 2021, 10, 3432–3443. [Google Scholar] [CrossRef]
- Pinki, F.T.; Khatun, N.; Islam, S.M. Content based paddy leaf disease recognition and remedy prediction using support vector machine. In Proceedings of the 2017 20th International Conference of Computer and Information Technology (ICCIT), Dhaka, Bangladesh, 22–4 December 2017; pp. 1–5. [Google Scholar]
- Militante, S.V.; Gerardo, B.D.; Medina, R.P. Sugarcane disease recognition using deep learning. In Proceedings of the 2019 IEEE Eurasia Conference on IoT, Communication and Engineering (ECICE), Yunlin, Taiwan, 3–6 October 2019; pp. 575–578. [Google Scholar]
- Jadhav, S.B.; Udupi, V.R.; Patil, S.B. Identification of plant diseases using convolutional neural networks. Int. J. Inf. Technol. 2021, 13, 2461–2470. [Google Scholar] [CrossRef]
- Astani, M.; Hasheminejad, M.; Vaghefi, M. A diverse ensemble classifier for tomato disease recognition. Comput. Electron. Agric. 2022, 198, 107054. [Google Scholar] [CrossRef]
- Kolluri, J.; Dash, S.K.; Das, R. Plant disease identification based on multimodal learning. Int. J. Intell. Syst. Appl. Eng. 2024, 12, 634–643. [Google Scholar]
- Eunice, J.; Popescu, D.E.; Chowdary, M.K.; Hemanth, J. Deep learning-based leaf disease detection in crops using images for agricultural applications. Agronomy 2022, 12, 2395. [Google Scholar] [CrossRef]
- Tammina, S. Transfer Learning Using VGG-16 with Deep Convolutional Neural Network for Classifying Images. Available online: https://www.ijsrp.org/research-paper-1019.php (accessed on 15 March 2024).
- Smith, J.; Johnson, A.; Davis, C. Automated Detection of Potato Late Blight Using Deep Learning and Transfer Learning Techniques. Agronomy 2023, 13, 1245. Available online: https://www.mdpi.com/2073-4395/13/6/1245 (accessed on 15 July 2024).
- Sheikh, M.H.; Mim, T.T.; Reza, M.S.; Rabby, A.S.A.; Hossain, S.A. Detection of Maize and Peach Leaf Diseases Using Image Processing. In Proceedings of the 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Kanpur, India, 6–8 July 2019; pp. 1–7. [Google Scholar] [CrossRef]
- Hossen, M.S.; Haque, I.; Islam, M.S.; Ahmed, M.T.; Nime, M.J.; Islam, M.A. Deep Learning Based Classification of Papaya Disease Recognition. In Proceedings of the 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS), Thoothukudi, India, 3–5 December 2020; pp. 945–951. [Google Scholar]
- Sarwinda, D.; Paradisa, R.H.; Bustamam, A.; Anggia, P. Deep Learning in Image Classification Using Residual Network (ResNet) Variants for Detection of Colorectal Cancer. Procedia Comput. Sci. 2021, 179, 423–431. [Google Scholar] [CrossRef]
- Liu, J.; Wang, M.; Bao, L.; Li, X. EfficientNet Based Recognition of Maize Diseases by Leaf Image Classification. J. Phys. Conf. Ser. 2020, 1693, 012148. [Google Scholar] [CrossRef]
- Spanhol, F.A.; Oliveira, L.S.; Petitjean, C.; Heutte, L. Breast Cancer Histopathological Image Classification Using Convolutional Neural Networks. In Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada, 24–29 July 2016; pp. 2560–2567. [Google Scholar]
- Espejo-Garcia, B.; Malounas, I.; Mylonas, N.; Kasimati, A.; Fountas, S. Using EfficientNet and Transfer Learning for Image-Based Diagnosis of Nutrient Deficiencies. Comput. Electron. Agric. 2022, 196, 106868. [Google Scholar] [CrossRef]
- Yang, H.; Ni, J.; Gao, J.; Han, Z.; Luan, T. A Novel Method for Peanut Variety Identification and Classification by Improved VGG16. Sci. Rep. 2021, 11, 15756. [Google Scholar] [CrossRef]
- Raza, R.; Zulfiqar, F.; Khan, M.O.; Arif, M.; Alvi, A.; Iftikhar, M.A.; Alam, T. Lung-EffNet: Lung Cancer Classification Using EfficientNet from CT-Scan Images. Eng. Appl. Artif. Intell. 2023, 126, 106902. [Google Scholar] [CrossRef]
- Huang, Z.; Su, L.; Wu, J.; Chen, Y. Rock Image Classification Based on EfficientNet and Triplet Attention Mechanism. Appl. Sci. 2023, 13, 3180. [Google Scholar] [CrossRef]
- Available online: https://www.kaggle.com/datasets/nafishamoin/bangladeshi-crops-disease-dataset (accessed on 11 June 2023).
- Atila, U.; Uçar, M.; Akyol, K.; Uçar, E. Plant leaf disease classification using EfficientNet deep learning model. Ecol. Inform. 2021, 61, 101182. [Google Scholar] [CrossRef]
- Padol, P.B.; Yadav, A.A. SVM classifier-based grape leaf disease detection. In Proceedings of the 2016 Conference on Advances in Signal Processing (CASP), Pune, India, 9–11 June 2016; pp. 175–179. [Google Scholar]
- Chaudhari, D.J.; Malathi, K. Detection and prediction of rice leaf disease using a hybrid CNN-SVM model. Opt. Mem. Neural Netw. 2023, 32, 39–57. [Google Scholar] [CrossRef]
- Tan, M.; Le, Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA, 9–15 June 2019; pp. 6105–6114. [Google Scholar]
- Stoica, G.; Stretcu, O.; Platanios, E.A.; Mitchell, T.; Póczos, B. Contextual parameter generation for knowledge graph link prediction. In Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA, 7–12 February 2020; Volume 34, pp. 3000–3008. [Google Scholar]
- Simeone, O. A very brief introduction to machine learning with applications to communication systems. IEEE Trans. Cogn. Commun. Netw. 2018, 4, 648–664. [Google Scholar] [CrossRef]
- Al Farid, F.; Hashim, N.; Abdullah, J.; Bhuiyan, M.R.; Kairanbay, M.; Yusoff, Z.; Karim, H.A.; Mansor, S.; Sarker, M.T.; Ramasamy, G. Single Shot Detector CNN and Deep Dilated Masks for Vision-Based Hand Gesture Recognition from Video Sequences. IEEE Access 2024, 12, 28564–28574. [Google Scholar] [CrossRef]
- Aabidi, M.H.; ELMakrani, A.; Jabir, B.; Zaimi, I. A Model Proposal for Enhancing Leaf Disease Detection Using Convolutional Neural Networks (CNN): Case Study. Int. J. Online Biomed. Eng. 2023, 19, 127. [Google Scholar] [CrossRef]
- Wang, P.; Fan, E.; Wang, P. Comparative analysis of image classification algorithms based on traditional machine learning and deep learning. Pattern Recognit. Lett. 2021, 141, 61–67. [Google Scholar] [CrossRef]
- Najafabadi, M.M.; Villanustre, F.; Khoshgoftaar, T.M.; Seliya, N.; Wald, R.; Muharemagic, E. Deep learning applications and challenges in big data analytics. J. Big Data 2015, 2, 1. [Google Scholar] [CrossRef]
- Yang, Y.; Cui, X. Bert-enhanced text graph neural network for classification. Entropy 2021, 23, 1536. [Google Scholar] [CrossRef] [PubMed]
- Yao, R.; Wang, N.; Liu, Z.; Chen, P.; Sheng, X. Intrusion detection system in the advanced metering infrastructure: A cross-layer feature-fusion CNN-LSTM-based approach. Sensors 2021, 21, 626. [Google Scholar] [CrossRef] [PubMed]
- Ma, Z.; Xu, Y.; Xu, H.; Meng, Z.; Huang, L.; Xue, Y. Adaptive batch size for federated learning in resource-constrained edge computing. IEEE Trans. Mob. Comput. 2021, 22, 37–53. [Google Scholar] [CrossRef]
- Dai, G.; Hu, L.; Fan, J. DA-ActNN-YOLOV5: Hybrid YOLO v5 model with data augmentation and activation of compression mechanism for potato disease identification. Comput. Intell. Neurosci. 2022, 2022, 6114061. [Google Scholar] [CrossRef]
Model | Traditional ML | Inception | CNN | ResNet | MobileNetV2 | VGGNet | YOLO | DenseNet | GoogleNet | EfficientNet |
---|---|---|---|---|---|---|---|---|---|---|
Paper [5] | ✓ | ✓ | ✓ | |||||||
Paper [8] | ✓ | |||||||||
Paper [12] | ✓ | ✓ | ✓ | ✓ | ||||||
Paper [13] | ✓ | |||||||||
Paper [14] | ✓ (RF) | ✓ | ✓ | ✓ | ||||||
Paper [15] | ✓ | |||||||||
Paper [16] | ✓ | |||||||||
Paper [17] | ✓ | |||||||||
Paper [18] | ✓ | ✓ | ✓ | ✓ | ||||||
Paper [19] | ✓ | |||||||||
Paper [20] | ✓ | |||||||||
Paper [21] | ✓ | ✓ | ✓ | ✓ | ✓ | |||||
Paper [22] | ✓ | |||||||||
Paper [23] | ✓ |
Stage i | Operator | Resolution | No. of Channels | No. of Layers |
---|---|---|---|---|
1 | Conv3×3 | 112 × 112 | 32 | 1 |
2 | MBConv1, k3×3 | 112 × 112 | 16 | 1 |
3 | MBConv6, k3×3 | 112 × 112 | 24 | 2 |
4 | MBConv6, k5×5 | 56 × 56 | 40 | 2 |
5 | MBConv6, k3×3 | 28 × 28 | 80 | 3 |
6 | MBConv6, k5×5 | 14 × 14 | 112 | 3 |
7 | MBConv6, k5×5 | 7 × 7 | 182 | 4 |
8 | MBConv6, k3×3 | 7 × 7 | 320 | 1 |
9 | Conv1×1 & Pooling & FC | 7 × 7 | 1280 | 1 |
Precision | Recall | F1-Score | Support | |
---|---|---|---|---|
Corn Common Rust | 1 | 1 | 1 | 800 |
Corn Healthy | 0.996264 | 1 | 0.9981285 | 800 |
Invalid Images | 1 | 1 | 1 | 800 |
Potato Healthy | 1 | 1 | 1 | 800 |
Potato Late Blight | 1 | 1 | 1 | 800 |
Rice Brown Spot | 1 | 0.9825 | 0.9868173 | 800 |
Rice Healthy | 0.9911728 | 0.99125 | 0.9887781 | 800 |
Accuracy | 0.99625 | 5600 | ||
Macro Average | 0.9962507 | 0.99625 | 0.9962463 | 5600 |
Weighted Average | 0.9962507 | 0.99625 | 0.9962463 | 5600 |
Precision | Recall | F1-Score | Support | |
---|---|---|---|---|
Corn Common_Rust | 1 | 1 | 1 | 200 |
Corn Healthy | 0.990099 | 1 | 0.9950249 | 200 |
Invalid Images | 1 | 1 | 0.9974937 | 200 |
Potato Healthy | 0.9848485 | 1 | 0.9798995 | 200 |
Potato Late Blight | 0.9752475 | 1 | 0.9800995 | 200 |
Rice Brown Spot | 0.952381 | 0.9825 | 0.9254499 | 200 |
Rice Healthy | 0.9095238 | 0.99125 | 0.9317073 | 200 |
Accuracy | 0.9728571 | 1400 | ||
Macro Average | 0.9731571 | 0.9728521 | 0.9728107 | 1400 |
Weighted Average | 0.9731571 | 0.9728521 | 0.9728107 | 1400 |
Model | Input Shape | Train Accuracy | Test Accuracy |
---|---|---|---|
CNN | 128, 128, 3 | 91.20% | 86.57% |
VGG16 | 128, 128, 3 | 85.98% | 83.29% |
ResNet50 | 128, 128, 3 | 71.75% | 68.79% |
Xceptiion | 128, 128, 3 | 95.05% | 94.07% |
Mobilenet V2 | 128, 128, 3 | 92.00% | 90.71% |
Autoencoders | 128, 128, 3 | 87.98% | 87.90% |
Inception v3 | 128, 128, 3 | 85.21% | 94.14% |
EfficientnetB0 | 128, 128, 3 | 98.025 | 96.14% |
Hybrid | 224, 224, 3 | 99.63% | 97.29% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Barman, S.; Farid, F.A.; Raihan, J.; Khan, N.A.; Hafiz, M.F.B.; Bhattacharya, A.; Mahmud, Z.; Ridita, S.A.; Sarker, M.T.; Karim, H.A.; et al. Optimized Crop Disease Identification in Bangladesh: A Deep Learning and SVM Hybrid Model for Rice, Potato, and Corn. J. Imaging 2024, 10, 183. https://doi.org/10.3390/jimaging10080183
Barman S, Farid FA, Raihan J, Khan NA, Hafiz MFB, Bhattacharya A, Mahmud Z, Ridita SA, Sarker MT, Karim HA, et al. Optimized Crop Disease Identification in Bangladesh: A Deep Learning and SVM Hybrid Model for Rice, Potato, and Corn. Journal of Imaging. 2024; 10(8):183. https://doi.org/10.3390/jimaging10080183
Chicago/Turabian StyleBarman, Shohag, Fahmid Al Farid, Jaohar Raihan, Niaz Ashraf Khan, Md. Ferdous Bin Hafiz, Aditi Bhattacharya, Zaeed Mahmud, Sadia Afrin Ridita, Md Tanjil Sarker, Hezerul Abdul Karim, and et al. 2024. "Optimized Crop Disease Identification in Bangladesh: A Deep Learning and SVM Hybrid Model for Rice, Potato, and Corn" Journal of Imaging 10, no. 8: 183. https://doi.org/10.3390/jimaging10080183
APA StyleBarman, S., Farid, F. A., Raihan, J., Khan, N. A., Hafiz, M. F. B., Bhattacharya, A., Mahmud, Z., Ridita, S. A., Sarker, M. T., Karim, H. A., & Mansor, S. (2024). Optimized Crop Disease Identification in Bangladesh: A Deep Learning and SVM Hybrid Model for Rice, Potato, and Corn. Journal of Imaging, 10(8), 183. https://doi.org/10.3390/jimaging10080183