학술논문

Leveraging Transfer Learning for Enhanced Plant Leaf Disease Detection
Document Type
Conference
Source
2024 International Conference on Automation and Computation (AUTOCOM) Automation and Computation (AUTOCOM), 2024 International Conference on. :153-158 Mar, 2024
Subject
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineering Profession
Power, Energy and Industry Applications
Signal Processing and Analysis
Training
Economics
Plant diseases
Microorganisms
Automation
Computational modeling
Transfer learning
Agriculture
Plant disease
Deep Learning
disease detection
ResNet152V2
Language
Abstract
Agriculture is a major sector on which the Indian economy depends. However, the varying weather conditions cause many plant diseases, which can impact the overall produce and thereby affects the Indian economy. Among many plant diseases, tomato leaf diseases are a common issue that affects tomato plants. These diseases can cause problems like spots, discoloration, wilting, and deformities on the leaves of tomato plants. This study used pictures of tomato leaves showing six diseases and healthy leaves. The dataset contained pictures of plant leaves showing diseases like early blight, late blight, bacterial spots, etc. The pictures were fed into a deep learning-based model, ResNet152V2, for the detection of diseases. The test results revealed the overall detection accuracy of 96.5%.