India, the world’s second-largest tomato producer, plays an essential role in feeding millions and providing substantial income for farmers. However, the backbone of Indian agriculture, the tomato, faces a significant challenge in early disease detection. Traditional disease detection methods, relying on expertise, prove time-consuming and prone to human error. The presence of undetected diseases poses a continual threat to the health and productivity of tomato plants, resulting in reduced yields and profits. To surpass these constraints and expedite the detection process, this paper employs a deep learning model built using a Convolutional Neural Network (CNN). The model follows a workflow involving image acquisition, pre-processing, extraction of features, and CNN training to identify diseases in tomato leaf plants. The proposed model exhibits an average score of detecting all tomato diseases categories with 98.27% of accuracy, 98.27% of precision, 97.81% of recall, and 98.06% of F1 score surpassing traditional approaches like SVM, KNN, and backpropagation.