Detection and Classification Process of Banana Leaf Diseases Using Convolutional Neural Networks (CNNs

Abstract

Finding and treating banana leaf diseases early helps farmers grow more crops and lose less. This matters most in places where bananas are a main food and income source. This thesis shows a new way to find and sort banana leaf diseases using a smart computer model. The model uses parts from two strong deep learning tools—Vision Transformer and ResNet50. It also uses an attention method to boost accuracy. The dataset, called BananaLSD, has leaf images from four groups: Cordana, Healthy, Pestalotiopsis, and Sigatoka. Before training the model, the images were cleaned and changed to help it learn better. Several models were tested, including pre-trained ResNet50, Vision Transformer, and a new hybrid CNN model. We used accuracy, F1- score, and confusion matrices to see how well they worked. The hybrid model with attention did the best. It had the highest accuracy and F1-score when sorting the diseases. This shows that using hybrid CNN models can help farmers spot crop problems sooner. It can also lead to better farming and less waste. The thesis also looks at how using AI in farming affects people, money, and the planet. The goal is to support fair, smart, and lasting ways to grow food. These findings show how tech can help solve real farming problems, like disease and food supply.