A Deep Learning-based Fine-tuned Convolutional Neural Network Model for Plant Leaf Disease Detection

The rapid proliferation of plant diseases poses a grave threat to global food security and agricultural productivity. To effectively address these challenges and ensure sustainable agricultural practices, the timely and accurate identification of diseases becomes paramount. Over recent years, deep learning techniques namely Convolutional Neural Networks (CNNs), have emerged as a pivotal tool with the potential to revolutionize plant disease identification by performing effective feature extraction. This study focuses on the development of a CNN model for automated plant disease identification. The dataset for the CNN implementation has been collected from Kaggel, which contains 32 varieties of plant leaf disease including normal leaves. The proposed model contains 13 different convolutional, 4 max pooling, 1 flattening and 1 dense layer for performance identification. This model has been implemented in four different scenarios by applying the model to the complete dataset with 5, 10, 15, and 20 epoch values. The results depict that the proposed model has shown the highest accuracy of 98.70% at epoch 20 while 97.87%, 95.92%, and 87.09% accuracies have resulted at epoch values 15, 10, and 5, respectively. The effectiveness of this model has been also compared with existing work which resulted in the proposed model achieving the highest accuracy.