Analysis of Techniques for Cotton Crop Disease Detection & Monitoring

Cotton is one of the most important crops in the world, playing an important role in the textile industry and contributing to the economy of many countries. However, cotton plants are susceptible to many diseases that reduce yield and quality. Early and accurate detection of these diseases is important for effective management and control, thus minimizing financial losses. Traditional diagnostic methods require expert judgment, are time-consuming and complex, and are generally impractical for large-scale applications. Therefore, there is interest in advances in machine learning and computer vision to develop automated systems for cotton disease prediction and detection. This project focuses on the development and evaluation of machine learning models for cotton leaf disease detection using Transfer Learning (TL) techniques and hybrid models. Cotton, being a vital crop, is susceptible to numerous diseases that can significantly affect yield and quality. Early detection and accurate classification of these diseases are crucial for timely intervention and minimizing economic losses. In this study, we applied several TL models, including VGG16 and VGG19, and assessed their performance using a comprehensive dataset of cotton leaf digital images.