Cocoa Diseases Classification using Deep Learning Algorithm

Abstract

This work addresses the critical issue of cocoa plant diseases, which pose a significant threat to global agriculture and the livelihood of millions of farmers. Convolutional Neural Networks (CNN) has been utilized for classifying cocoa diseases, focusing on combating the significant agricultural and economic impacts of black pod rot and pod borer. Utilizing a dataset of 4390 images, five CNN architectures—Custom CNN, VGG-16, EfficientNetB0, ResNet50, and LeNet-5—were assessed for their ability to accurately identify disease presence. The Custom CNN model was found to be the most effective, achieving an accuracy of 91.79%, precision of 91.79%, recall of 91.79%, F1 score of 82.08%, sensitivity of 96.69%, and specificity of 98.40%, indicating its strong capability in correctly classifying both healthy and diseased plants. The work methodically approached data preprocessing, model parameter tuning, and a structured machine learning evaluation process. While EfficientNetB0 and ResNet50 also displayed commendable performances, VGG-16 and LeNet-5 lagged, suggesting the need for further model refinement. This work underscores the importance of the F1 score in evaluating model performance, especially given the class imbalance within the dataset. The findings suggest future exploration into other pre-trained models and data augmentation strategies to further enhance classification accuracy. The goal of this work is the implementation of a realtime system to minimize cocoa production losses due to disease.