Abstract

In India, cotton holds a significant position as a key cash crop. Despite its economic importance, cotton crops are subject to a variety of illnesses that can reduce output and quality. Early detection of these diseases is crucial for minimizing damage and preserving the crop. Cotton is vulnerable to diverse ailments, includes powdery mildew, leaf curl, bacterial blight, target spot, leaf spot, and nutrient deficits. To put effective mitigation methods into place, it is imperative that one correctly recognizes these illnesses. The prevalence of cotton leaf diseases poses a substantial challenge for Indian farmers. This paper proposes the application of machine learning, specifically Convolutional Neural Networks (CNN), for disease detection as a promising solution. Leveraging technology for disease identification can empower farmers to take prompt actions, mitigating the risk of significant crop losses. Machine learning, with its demonstrated success in various domains, including agriculture, offers valuable tools for disease detection and classification. CNNs, known for their proficiency in image-related tasks, can learn to recognize disease-specific patterns in plant leaves. This paper contributes by conducting a comprehensive review of prior research on crop disease detection and introducing an innovative approach that makes use of artificial intelligence techniques to detect illnesses in cotton leaves.