Using Transfer Learning for Image-Based Cassava Disease Detection

TL;DR

This paper demonstrates that transfer learning with deep convolutional neural networks can accurately and efficiently detect multiple cassava diseases and pest damages from field images, supporting scalable disease management in sub-Saharan Africa.

Contribution

It introduces a transfer learning approach for cassava disease detection using field images, achieving high accuracy and enabling deployment on mobile devices.

Findings

Achieved up to 98% accuracy for certain diseases.

Overall accuracy of 93% on unseen data.

Demonstrated feasibility of mobile deployment for disease detection.

Abstract

Cassava is the third largest source of carbohydrates for human food in the world but is vulnerable to virus diseases, which threaten to destabilize food security in sub-Saharan Africa. Novel methods of cassava disease detection are needed to support improved control which will prevent this crisis. Image recognition offers both a cost effective and scalable technology for disease detection. New transfer learning methods offer an avenue for this technology to be easily deployed on mobile devices. Using a dataset of cassava disease images taken in the field in Tanzania, we applied transfer learning to train a deep convolutional neural network to identify three diseases and two types of pest damage (or lack thereof). The best trained model accuracies were 98% for brown leaf spot (BLS), 96% for red mite damage (RMD), 95% for green mite damage (GMD), 98% for cassava brown streak disease (CBSD), and 96% for cassava mosaic disease (CMD). The best model achieved an overall accuracy of 93% for data not used in the training process. Our results show that the transfer learning approach for image recognition of field images offers a fast, affordable, and easily deployable strategy for digital plant disease detection.