Performance Evaluation of Cotton Leaf Disease Detection Using Deep Learning Models

Cotton plant diseases significantly impact developing nations' economies and pose a threat to the textile industry. Detecting these diseases is challenging due to lack of competence and fluctuating disease stages. Recent technology has enabled the use of computer-aided techniques to automatically identify and categorize disorders. This paper proposes various deep learning approaches for identifying and categorizing cotton leaf diseases, focusing on unhealthy and unhealthy areas. The study uses a dataset and various optimization techniques, with the Xception model showing the highest validation accuracy of 98.61% using the Adam optimizer.