Plant diseases persistently challenge farmers, affecting their income and food production. Even experts in the field find it difficult to contain the spread of these diseases once they take hold within a plant. While experts can identify and diagnose the ailments through close inspection of affected areas, smallholder farmers, who constitute a significant portion of the population, often lack access to such expertise. There is a need for an effective approach to identify plant leaf diseases and assess their stages. Owing to the ongoing internet revolution and advancements in computer vision models, the agricultural sector can now harness computer vision techniques. Convolutional Neural Networks (CNNs) stand out as the most advanced approach for image classification, offering precise diagnoses. This proposal leverages a deep learning module developed through Transfer Learning to diagnose plant diseases via a web-based application. A pre-trained model was created using images of diverse plant leaves from the Plant Village dataset, enabling the identification and diagnosis of diseases. To gauge the effectiveness of this approach, various performance metrics such as Precision, Recall, F1-score, and accuracy were computed and continuously monitored. The proposal achieved an impressive accuracy rate of nearly 95% with the ResNet50 model and the Plant Village Dataset. This initiative has the potential to revolutionize farming practices and bolster food production.