Plant Disease Detection

Abstract

Plant diseases are a major challenge in agriculture, often resulting in decreased crop productivity and financial losses. This research introduces an automated Plant Disease Prediction System that utilizes deep learning, specifically Convolutional Neural Networks (CNNs), to detect diseases from plant leaf images. The system reduces reliance on manual inspection by providing fast and reliable disease identification.

A labeled dataset of plant leaf images is used to train the CNN model, with particular attention given to diseases such as powdery mildew and rust. By extracting and learning key visual features, the model can accurately classify plant health conditions. The trained model is deployed through a web-based platform developed using Flask and Streamlit, enabling users to upload images and receive immediate predictions.

Although the system achieves strong performance, challenges such as improving generalization across different plant species and optimizing the model for real-world deployment remain. Future enhancements will focus on expanding the dataset, improving efficiency, and enabling mobile-based access. This work highlights the potential of AI-driven solutions in promoting sustainable agriculture and improving food production systems.