PepperShield: Disease Detection with Hyper Tuned Precision

A popular vegetable crop, bell peppers (Capsicum annuum) are prized for both their economic significance and nutritional advantages. Bell peppers, like many other crops, are prone to a number of illnesses brought on by bacteria, fungi, viruses, and environmental conditions. These diseases can drastically lower the harvest's quality and output. Preventing crop losses and guaranteeing food security depends on the early identification and precise classification of these diseases. Conventional plant disease detection techniques usually entail professional manual inspection, which can be expensive, time-consuming, and prone to human mistakes. Recent developments in machine learning and artificial intelligence (AI) have opened new possibilities for automating agricultural disease diagnosis. By contrasting two different models, one created from scratch and the other improved with hyperparameter tuning, this effort seeks to utilize CNNs' potential for bell pepper disease prediction and classification. The main goal is to investigate how CNN model performance is affected by adjusting important hyperparameters like learning rate, batch size, and the number of training epochs. Metrics including accuracy, precision, recall, and F1-score will be used to train and assess the models using preprocessed picture data of both healthy and diseased bell peppers. By providing a scalable, AI-driven method for real-time disease diagnosis in bell pepper crops, this research holds significance for precision agriculture.