Earlier Detection of Plant Disease and Recommending Pesticides using Convolutional Neural Network

Plant disease detection systems may face challenges in accurately distinguishing between various diseases, especially when symptoms overlap or environmental factors introduce ambiguity, impacting the system’s reliability. The agricultural innovation described involves an integrated system for early plant disease detection and targeted pesticide recommendations. It utilizes preprocessing, feature extraction, and advanced classification algorithms. Data from IoT sensors and high-resolution imaging devices are collected to monitor crop conditions and remove image noise using Gaussian smoothing. Feature extraction, particularly the Histogram Oriented Gradients method, is employed to identify disease symptoms and environmental parameters. Advanced machine learning algorithms, including Convolutional Neural Networks (CNN), are used to classify diseases and recommend pesticides based on disease type, severity, crop, and environmental conditions. This innovation enhances timely disease identification and promotes more precise and sustainable pesticide use, leading to increased agricultural productivity and reduced environmental impact. MATLAB is used for research evaluation, showing 7% superior performance compared to existing methodologies.