Hyperparameter-Tuned CNN for the Classification of Ten Tomato Plant Diseases

Tomato plant diseases caused by microorganisms such as fungus, bacterial etc. have been threatening the quality and quantity of tomato production for a few centuries. Therefore, precaution is necessary during the early stage to detect and cure the diseases that occurred on the leaves before the diseases spread to result in plant death. However, the detection method employed currently is inconsistent and inefficient. Most farmers employ manual visualisations to identify the types of plant diseases as the automatic monitoring and classification of diseases cannot be achieved. Such obstacles drive the need for a plant disease detection system, aided by artificial intelligence (AI). Therefore, in this work, four different Convolutional Neural Network (CNN) models for tomato plant diseases detection, namely VGG-16, ResNet-50, DenseNet-121 and ResNet-101 were implemented and the hyperparameters were manipulated for parametric studies. The performance of the different architectures with the selected hyperparameters was evaluated and compared according to the well-established evaluation metrics for deep learning; Precision, Recall, F1 score, Matthews correlation coefficient (MCC) and Accuracy. Combining all its merits, the ResNet-50 model which had achieved an accuracy of 100% with a shorter training time was proposed as the final model to be implemented in the tomato plant diseases classification system. In short, a CNN model that is capable of effective classification of tomato leaf diseases has been developed and its benefits for tomato cultivation are much anticipated.