Detecting Plant Leaf Diseases with Convolutional Neural Networks (CNN) and Deployment via Hugging Face

• Published in: 2024 International Conference on Power, Energy, Control and Transmission Systems (ICPECTS) pp. 1 - 6
• Main Authors: Prabahar Godwin James, T., J, Pathmanaban, G, Vivekanandan, M S, Anantha Karthigeyan, R, Deepak, J, Abdul Kalam
• Format: Conference Proceeding
• Language: English
• Published: IEEE 08.10.2024
• Subjects: Agricultural Technology; Convolutional Neural Network; Convolutional neural networks; Crops; Deep Learning; Diseases; Face recognition; Farming; Hugging Face; Image Classification; Plant Disease Detection; Plants (biology); Precision agriculture; Prevention and mitigation; Productivity; Real-time systems; Sustainable Farming Practices; Tomato Leaf Disease
• DOI: 10.1109/ICPECTS62210.2024.10780036

Ensuring food security relies heavily on agriculture, and any threat to crop health can significantly impact local economies and populations. Detecting and addressing plant diseases early poses a challenge for farmers. This study presents a novel approach for identifying leaf diseases in plants, focusing specifically on tomato and potato leaves. A deep learning model using Convolutional Neural Networks (CNN) was developed with 91% accuracy to recognize up to 13 different diseases affecting these plants. The dataset used includes high-resolution images of both healthy and diseased leaves, enabling precise classification. The model is deployed on Hugging Face, making it accessible and scalable for real-time applications in assisting farmers and agricultural specialists with disease detection and prevention. This solution enhances crop health monitoring, leading to improved agricultural productivity and reduced pesticide usage, contributing to precision agriculture and sustainable farming practices.