Evaluating Data Augmentation Techniques for Coffee Leaf Disease Classification

TL;DR

This paper explores the use of deep learning, including CycleGAN and Transformer models, to improve coffee leaf disease classification using the imbalanced RoCoLe dataset, demonstrating that synthetic augmentation enhances model accuracy.

Contribution

It introduces the application of CycleGAN-based augmentation and Transformer models to coffee leaf disease classification, addressing dataset imbalance and improving detection accuracy.

Findings

CycleGAN augmentation improves classification performance.

Transformer models outperform traditional CNNs.

Synthetic data complements real data effectively.

Abstract

The detection and classification of diseases in Robusta coffee leaves are essential to ensure that plants are healthy and the crop yield is kept high. However, this job requires extensive botanical knowledge and much wasted time. Therefore, this task and others similar to it have been extensively researched subjects in image classification. Regarding leaf disease classification, most approaches have used the more popular PlantVillage dataset while completely disregarding other datasets, like the Robusta Coffee Leaf (RoCoLe) dataset. As the RoCoLe dataset is imbalanced and does not have many samples, fine-tuning of pre-trained models and multiple augmentation techniques need to be used. The current paper uses the RoCoLe dataset and approaches based on deep learning for classifying coffee leaf diseases from images, incorporating the pix2pix model for segmentation and cycle-generative adversarial network (CycleGAN) for augmentation. Our study demonstrates the effectiveness of Transformer-based models, online augmentations, and CycleGAN augmentation in improving leaf disease classification. While synthetic data has limitations, it complements real data, enhancing model performance. These findings contribute to developing robust techniques for plant disease detection and classification.