Smart Farming: Deep Learning for Accurate Plant Leaf Disease Diagnosis
Main Article Content
Abstract
This paper presents a strong deep learning framework for automatically diagnosing plant leaf diseases, which is a step forward in precision agriculture. The method combines two high-performing models, MobileNetV2 and EfficientNet, using a broad dataset of CLAHE-enhanced images of 15 diseased and healthy plant classes. The first steps in preprocessing include converting the image to greyscale and shrinking it to 256×256 pixels. Then, the Grey Level Co-occurrence Matrix (GLCM) is used to extract texture features that show important patterns. We use important measures like accuracy, precision, recall and loss to judge how well a model works. MobileNetV2 does better than older models like VGG19 (87%) and InceptionV3 (84%) with an accuracy of 97.38%. EfficientNet does well too, with an accuracy of 93.8%. The suggested models are reliable and effective, as shown by comparative assessments, confusion matrices and cross-validation. They greatly reduce the number of misclassifications. The results show that deep learning could be a reliable and scalable way to discover diseases early and better manage crops in precision farming.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
M. H. Hossen, M. Mohibullah, C. S. Muzammel, T. Ahmed, S. Acharjee and M. B. Panna, “Wheat Diseases Detection and Classification using Convolutional Neural Network (CNN),” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 11, pp. 719–726, 2022, doi: 10.14569/IJACSA.2022.0131183.
A. Fuentes, S. Yoon, S. C. Kim and D. S. Park, “A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition,” Sensors (Switzerland), vol. 17, no. 9, 2017, doi: 10.3390/s17092022.
N. G. Rezk, A. F. Attia, M. A. El-Rashidy, A. El-Sayed and E. E. D. Hemdan, “An Efficient Plant Disease Recognition System Using Hybrid Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs) for Smart IoT Applications in Agriculture,” Int. J. Comput. Intell. Syst., vol. 15, no. 1, pp. 1–21, 2022, doi: 10.1007/s44196-022-00129-x.
M. J. Karim, M. O. F. Goni, M. Nahiduzzaman, M. Ahsan, J. Haider and M. Kowalski, “Enhancing agriculture through real-time grape leaf disease classification via an edge device with a lightweight CNN architecture and Grad-CAM,” Sci. Rep., vol. 14, no. 1, pp. 1–23, 2024, doi: 10.1038/s41598-024-66989-9