Abstract
Plant diseases have presented substantial hurdles to the agricultural industry in recent years, potentially resulting in lower crop yield and financial losses. Traditional disease detection methods usually rely on manual inspection, which can be time-consuming and prone to human mistakes. Our AI- Powered Plant Disease Detection System overcomes these issues by leveraging cutting-edge machine learning and artificial intelligence technology. This technology uses powerful image recognition algorithms to swiftly and precisely identify and diagnose plant illnesses. By analyzing photos of plant leaves and other components, the AI model may be able to detect early sickness symptoms, allowing for better disease control and earlier intervention. Plant diseases have a considerable influence on agricultural output, resulting in monetary losses and food shortages. Early and precise identification of plant illnesses is critical for prompt intervention, which can reduce the spread of infections and increase crop output. Manual examination is frequently used in traditional plant disease detection procedures. With advances in machine learning (ML) and deep learning (DL), automated plant disease detection systems have emerged as reliable options. Using datasets including photos of healthy and sick plants, the suggested technique seeks to achieve high accuracy, precision, recall, and F1-score while minimizing misclassification as indicated by the confusion matrix. The technique investigates a variety of machine learning and deep learning models, including basic methods such as Support Vector Machines (SVM) and Random Forests (RF), as well as sophisticated Convolutional Neural Networks (CNNs) and transformer-based architectures. Preprocessing methods like feature extraction and picture augmentation are used to make the models more resilient. The suggested technique is suited for practical implementation in agricultural settings as evaluation metrics guarantee that it not only detects illnesses with high precision but also reduces false positives and negatives.