Plant diseases present a substantial challenge for farmers, causing significant
crop losses and diminishing yields. Timely detection and effective treatment are
crucial, yet traditional methods often fall short due to their reliance on human expertise
and the potential for misdiagnosis. These conventional approaches can be slow and
cumbersome, leading to delays in addressing plant health issues. Our proposed system
addresses these challenges by employing Convolutional Neural Networks (CNNs) for
precise and efficient leaf disease detection and targeted fertilizer recommendations.
Using CNNs for image classification, the system can accurately identify plant diseases
from leaf images and suggest appropriate fertilizers, thereby optimizing treatment
strategies. This CNN-based approach was rigorously tested on a comprehensive dataset
of plant leaf images, demonstrating impressive accuracy in disease detection and
fertilizer recommendations. The system's advanced capabilities streamline the
diagnostic process and enhance crop yield by providing farmers with timely and
precise recommendations. Integrating CNN-based analysis with actionable insights
reduces reliance on extensive human expertise and fosters more sustainable and
efficient farming practices.
Keywords: Convolutional neural network, Internet of Things, Machine Learning, Multiple linear regression.
