Leaf Disease Predictions Using Deep Learning Techniques - Potato

Abstract

The Study of leaf diseases is important to obtain healthy crop yields and confirm food security. Detection of potato leaf diseases at an early stage is of great significance to the agricultural industry. Detecting this disease early helps farmers protect their plants. But soil and climate pollution are highly unfavorable for potato growth and it leads to disease such as scab, black scurf, blackleg, dry rot, and pink rot.
Though, identifying diseases in potato leaves is challenging because of the composite symptoms and variability in leaf presences. This involves the advance of an operative and efficient method that can overcome these contests and improve disease detection accuracy. Predicting potato leaf disease at early stage is crucial and this research paper proposes a deep machine learning approach utilizing Convolutional Neural Network Especially Residual Network50 Version 2(ResNet50V2) model that can rapidly and accurately identify plant disease. The comparative study of the leaf disease works on three models CNN, EfficientB0, ResNet50V2 model. Comparing these models the study reached the expected testing and train accuracy. The study highlights the importance of feature fusion and predicting early leaf disease in enhancing disease diagnoses.