Optimization of Machine Learning Models for Potato Disease Classification

Abstract

This project focuses on the classification of potato leaf diseases using computer vision techniques. Potato crops are particularly vulnerable to various foliar diseases that can significantly reduce yield and quality. To address this challenge, we developed a system that leverages image processing and machine learning methods to automatically identify and classify infected leaves. Our approach involves data collection, preprocessing of leaf images, feature extraction, and the application of deep learning models for classification. The results demonstrate promising accuracy and effectiveness, proving that such systems can assist farmers and agricultural experts in early disease detection and decision-making. This work contributes to the broader field of precision agriculture, aiming to enhance crop health monitoring and sustainable farming practices.