High-Performance Deep Learning Techniques for Plant Disease Detection: Performance Analysis, Validation, and Applications

The early detection of plant diseases is an indispensable task to improve crop yields and production quality. Crop disease observations by experienced pathologists are difficult and might take a long time. Therefore, deep learning (DL) techniques have been utilized to present an automated detection technique that could accurately and timely detect plant diseases. Several DL models in the literature were proposed, but no paper conducted a comparative study between those models to determine which of them was the best alternative for this task. Therefore, twenty-one DL models are compared in this review paper to show which of them could achieve better classification accuracy when applied to detect plant diseases. Three publicly available datasets, namely PlantVillage, Tomato Leaves, and Groundnut Plant Leaf, are used to assess the performance of those models under five different performance metrics, such as accuracy, precision, recall, F1-score, and area under curve (AUC). The extensive experiments conducted in the same environments under the same number of epochs and batch size for all models show that EfficientNetB0 is the best for both PlantVillage and Tomato Leaves datasets, with a classification accuracy of around 99% and 98%, respectively, and ResNet152 is the best for the Groundnut Plant Leaf dataset, with a classification accuracy of 99.7%.