Author:
Rajamohanan Rajasree,Latha Beulah Christalin
Abstract
Deep learning has gained widespread adoption in various fields, including object recognition, classification, and precision agriculture. This study aimed to investigate the use of deep convolutional neural networks for the real-time identification of diseases in tomato plant leaves. A customized field dataset was constructed, consisting of several images of tomato leaves captured using a mobile phone from agricultural fields in the Kerala and Tamil Nadu regions and classified into two categories: healthy and diseased. A YOLO v5 deep learning model was trained to classify images of tomato leaves into the respective categories. This study aimed to determine the most effective hyperparameters for the classification and detection of healthy and sick leaves sections, using both proprietary and publicly available datasets. The YOLO v5 model demonstrated a notable accuracy rate of 93% when evaluated in the test dataset. This method can help farmers quickly recognize diseased leaves and prompt the implementation of preventive measures to curtail the spread of tomato plant diseases.
Publisher
Engineering, Technology & Applied Science Research
Reference42 articles.
1. Ramanjot et al., "Plant Disease Detection and Classification: A Systematic Literature Review," Sensors, vol. 23, no. 10, Jan. 2023, Art. no. 4769.
2. R. I. Hasan, S. M. Yusuf, and L. Alzubaidi, "Review of the State of the Art of Deep Learning for Plant Diseases: A Broad Analysis and Discussion," Plants, vol. 9, no. 10, Oct. 2020, Art. no. 1302.
3. S. Arivazhagan, R. N. Shebiah, S. Ananthi, and S. V. Varthini, "Detection of unhealthy region of plant leaves and classification of plant leaf diseases using texture features," Agricultural Engineering International: CIGR Journal, vol. 15, no. 1, pp. 211–217, Apr. 2013.
4. K. Lin, L. Gong, Y. Huang, C. Liu, and J. Pan, "Deep Learning-Based Segmentation and Quantification of Cucumber Powdery Mildew Using Convolutional Neural Network," Frontiers in Plant Science, vol. 10, 2019.
5. J. Blumenthal, D. B. Megherbi, and R. Lussier, "Supervised machine learning via Hidden Markov Models for accurate classification of plant stress levels & types based on imaged Chlorophyll fluorescence profiles & their rate of change in time," in 2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA), Annecy, France, Jun. 2017, pp. 211–216.