Classification of Tomato Leaf Disease Using CNN Merge Model

Abstract

Tomato leaf diseases provide a significant and widespread challenge to agri- cultural output, particularly in places such as Bangladesh. This research proposes an innovative artificial intelligence (AI) approach that employs a Convolutional Neural Network (CNN) Merge Model to accurately detect diseases in tomato leaves. The model’s strong performance, characterised by an accuracy rating of 0.9835, precision of 0.9835, and recall of 0.9835, highlights its efficacy in tackling this significant concern.The primary inno- vation of this study involves the incorporation of Res-Net50 and MobileNet conventional neural network (CNN) architectures.In addition to its first achievements, this research establishes a foundation for revolutionary agri- cultural methodologies.In our future plans, we anticipate the expansion of the data-set to include a wider range of tomato leaf diseases.Additionally, we aim to investigate the potential applicability of the model to other crop diseases. These endeavours possess the potential to significantly transform not just the management of tomato crops but also the agricultural sector on a broader scope.In summary, this research demonstrates the efficacy of AI-based solutions in addressing urgent agricultural issues, thereby paving the way for a more environmentally friendly and productive agricultural industry in Bangladesh and other regions.