Automated Detection and Classification of Cotton Leaf Diseases: A Computer Vision Approach

Cotton plays a vital role in agricultural sustainability, extending beyond its textile applications. Pathogens pose significant threats to cotton plants and farmers' livelihoods, highlighting the critical need for disease detection to maintain crop health and ensure optimal yields. Our research pioneers a novel approach to disease detection in cotton through advanced image analysis techniques. This involves exploring deep learning methodologies specifically tailored for detecting cotton leaf diseases and enhancing accuracy by integrating CNN models, while balancing labor intensity and cost considerations. Leveraging the Convolutional Neural Networks (CNN), the combination of the interpretability of Densenet 121 with the stability of ResNet 50, assessing the strength of their combined algorithm. This hybrid model accurately classifies various cotton plant diseases, enabling fine-grained analysis. With a precision-driven approach, the proposed model achieves exceptional results, accurately identifying six distinct diseases, including fungal, bacterial, and viral pathogens, with an impressive 96% accuracy rate. The research aims to provide a comprehensive and dependable solution for disease management in the cotton industry, ultimately promoting crop health, productivity, and sustainability