Rasel, Annajiat AlimKarim, Dewan ZiaulHasan Mahin, Mohammad RakibulMoonwar, WaheedRayhan Chy, Md. ShamsulShahriar, Md. FahimRafi, Fahim Faisal2024-01-172024-01-1720232023-01ID: 20201220ID: 20201219ID: 19201109ID: 19201046ID: 19201081http://hdl.handle.net/10361/22178Cataloged from PDF version of thesis.Includes bibliographical references (pages 76-83).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.Agriculture has consistently been an essential component of our day-to-day life over the centuries. Because of its contribution to our country’s revenue, the importance of agriculture has been steadily growing over the course of the years. However, there are some counter factors that prevent us from reaping the full benefits that crops have to offer. The presence of a wide variety of natural diseases on plant leaves is one such factor. The most prominent causes of these problems are typically severe weather conditions and excessive use of pesticides, both of which put a strain on the economy of Bangladesh as a whole. To reduce the severity of the problem, we are going to design an image processing system that utilizes Deep Learning and Convolutional Neural Networks (CNN) to classify plant leaf diseases. Our primary demographic of interest consists of farmers and other people willing to tend to crops. We have concluded that the best way to go about this is by constructing a website and making it as simple and straightforward as possible. The user will select im ages of the diseased leaf, and our CNN model will predict and categorize the leaf’s condition based on the chosen images. After implementing CNN, we introduce another model, namely LIME, which is based on the concept of Explainable AI (XAI). An XAI is an artificial intelligence that mainly helps humans to understand the decisions or predictions made by an AI. In this scenario, after our CNN model classifies the diseased leaves, the XAI aids us in understanding the reason and cause behind the leaves mentioned above being classified as how they are by the CNN model. Conclusively, following the completion of running our models, we managed to get a 99.54% accuracy rate in our testing phase.83 pagesenBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Neural networkConvolutional Neural Network (CNN)Plant leaf disease identificationDeep learningXAIImage processingCognitive learning theory (Deep learning)Plant diseases--DiagnosisThesis