TPC Net: An Efficient CNN Architecture for Tomato Plant Disease and Pest Classification
Ovidiu Cosma, Laura Cosma

Abstract. Tomato crops are affected by a wide variety of diseases and pests that can dramatically reduce both yield and quality. This paper presents TPC_Net, an efficient convolutional neural network architecture for tomato plant disease and pest classification. The model is trained on images from the PlantVillage and TomatoVillage datasets, using a balanced subset created through augmentation techniques. TPC_Net is compared with established models adapted for tomato disease classification, demonstrating superior accuracy, precision and recall in identifying 11 distinct classes of diseases and pests. The streamlined architecture of TPC_Net facilitates deployment in mobile applications, promising significant advancements in agricultural technology for effective disease management.

Keywords: convolutional neural networks; tomato disease; pest classification; PlantVillage; precision agriculture

Ovidiu Cosma, Laura Cosma, "TPC Net: An Efficient CNN Architecture for Tomato Plant Disease and Pest Classification", Proc. 19th SOCO Int. Conf. on Soft Computing Models in Industrial and Environmental Applications, Springer, 2024, 2023. DOI: https://doi.org/10.1007/978-3-031-75010-6_19.

Reference: Proc. 19th SOCO Int. Conf. on Soft Computing Models in Industrial and Environmental Applications, Springer, 2024. DOI: 10.1007/978-3-031-75010-6_19

Other publications