Image Classification for CSSVD Detection in Cacao Plants

TL;DR

This paper develops and evaluates image classifiers using VGG16, ResNet50, and ViT to detect CSSVD in cacao plants, achieving high accuracy and recall on a publicly available dataset, addressing data scarcity issues.

Contribution

The study introduces effective image classifiers for CSSVD detection in cacao plants, utilizing transfer learning models and a new dataset, with ResNet50 showing superior performance.

Findings

ResNet50 classifier achieved 94.34% F1-score.

Recall improved by 9.75% over previous methods.

High accuracy demonstrates potential for practical CSSVD detection.

Abstract

The detection of diseases within plants has attracted a lot of attention from computer vision enthusiasts. Despite the progress made to detect diseases in many plants, there remains a research gap to train image classifiers to detect the cacao swollen shoot virus disease or CSSVD for short, pertinent to cacao plants. This gap has mainly been due to the unavailability of high quality labeled training data. Moreover, institutions have been hesitant to share their data related to CSSVD. To fill these gaps, we propose the development of image classifiers to detect CSSVD-infected cacao plants. Our proposed solution is based on VGG16, ResNet50 and Vision Transformer (ViT). We evaluate the classifiers on a recently released and publicly accessible KaraAgroAI Cocoa dataset. Our best image classifier, based on ResNet50, achieves 95.39\% precision, 93.75\% recall, 94.34\% F1-score and 94\% accuracy on only 20 epochs. There is a +9.75\% improvement in recall when compared to previous works. Our results indicate that the image classifiers learn to identify cacao plants infected with CSSVD.