Innovative Approaches in Tomato Leaf Disease Recognition using Deep Learning

The precise and prompt identification of plant diseases is of utmost significance in the field of agricultural technology. In order to classify tomato leaf diseases, this work gives a thorough comparison of many deep learning models. To help in the early identification and treatment of a variety of illnesses that affect tomato plants, this research seeks to determine the most efficient model for disease diagnosis. The study used a dataset of 20,000 photographs, each 768 by 768 pixels in size and divided into 10 different groups. These classes represented several tomato leaf ailments, such as Septoria Leaf Spot, Target Spot, Bacterial Spot, Tomato Yellow Leaf Curl Virus, Late Blight, Leaf Mould, and Early Blight. They also included spider mites and two-spotted spider mites. 2,000 photos were distributed equally among each class, guaranteeing fair representation in all categories.This study used ResNetl52V2, ResNet50, VGG19, and Inception v2 as its four DL models. On the basis of accuracy, precision, recall, and F1-score, each model was trained and assessed using the dateset. The Inception v2 model fared better than the others, showing improved accuracy and precision in illness categorization, according to the data. This study highlights how DL might transform the way plant diseases are found and managed. The results imply that the higher performance of the Inception v2 model makes it potentially useful for the early identification and categorization of tomato leaf diseases. This might greatly improve crop management techniques, resulting in increased output and sustainability in the tomato agricultural industry. In order to further widen the applicability of DL: in agricultural technology, future study may examine the application of this model to additional crops and illnesses.