Deep Learning-Based Plant Disease Detection Using Convolutional Neural Networks with Web and Mobile Deployment

Agricultural productivity is a primary driver of global food security; however, the proliferation of plant diseases remains a significant threat to crop yield and quality. While early detection is critical to mitigating these losses, manual identification is often inefficient and prone to error. This paper proposes a robust automated classification framework leveraging Convolutional Neural Networks (CNNs) for the rapid identification of plant pathologies. By training on a diverse, labeled dataset of foliar imagery and employing data augmentation techniques to enhance model generalization, the proposed system achieves high classification accuracy across multiple species and disease classes. Furthermore, the model is integrated into a mobile-accessible web application, facilitating real-time diagnostic capabilities in field conditions. Experimental results validate the system’s reliability and performance, demonstrating its potential as a scalable solution for smart agriculture and precision crop management.