Abstract
Plant leaf disease identification is a crucial aspect of modern agriculture to enable early disease detection and prevention. Deep learning approaches have demonstrated amazing results in automating this procedure. This paper presents a comparative analysis of various deep learning methods for plant leaf disease identification, with a focus on convolutional neural networks. The performance of these techniques in terms of accuracy, precision, recall, and F1-score, using diverse datasets containing images of diseased leaves from various plant species was examined. This study highlights the strengths and weaknesses of different deep learning approaches, shedding light on their suitability for different plant disease identification scenarios. Additionally, the impact of transfer learning, data augmentation, and sensor data integration in enhancing disease detection accuracy is discussed. The objective of this analysis is to provide valuable insights for researchers and practitioners seeking to harness the potential of deep learning in the agricultural sector, ultimately contributing to more effective and sustainable crop management practices.
Publisher
The Electrochemical Society
Reference77 articles.
1. Plant disease identification using deep neural networks;P. R.-T. J. of, and undefined 2017;Jmis.Org,2017
2. Identification of plant disease infection using soft-computing: Application to modern botany;Kiani;Procedia Comput Sci,2017
3. Metaheuristic techniques for classification used in identification of plant diseases;Bala;ECS Trans.,2022
4. Total internal reflection of two lasers in a single planar optical waveguide;Kocheril;ECS Sensors Plus,2022
5. Identification of rice plant diseases using image processing, machine learning & deep learning: a review;Bala;CEUR Workshop Proc,2021