Publication

Abstract : In India, where agriculture sustains over 70% of the population, the impact of millet diseases on crop yield and economic outcomes for farmers cannot be overstated. With the advent of digitalization permeating various sectors, including agriculture, leveraging technology becomes imperative for enhancing productivity and ensuring food security. The ability to detect and manage Millet's diseases efficiently is crucial for maximizing crop yield and minimizing losses. Deep learning, mostly Convolutional Neural Networks (CNNs), has appeared as well as an influential tool in digital image processing, offering significant advantages over traditional methods. Leveraging CNNs for the recognition and categorization of Millet's diseases presents a promising solution to this longstanding challenge. The process of Millet's disease detection using CNN involves several key steps, together with acquiring images, initialization, partition, division, as well as disease identification. In conclusion, the integration of CNN-based Millet's disease detection systems holds immense potential for revolutionizing agricultural practices in India. By connecting the supremacy of deep learning and digitalization, stakeholders can work towards confirming food security, increasing farm profitability, and promoting supportable agricultural practices. In this article, we obtained a 97.8% accuracy in detecting Plant diseases using a CNN-based approach.