Using Transfer Learning for Image-Based Cassava Disease Detection
This provides a fast, affordable, and deployable solution for digital plant disease detection, addressing food security threats in sub-Saharan Africa, but it is incremental as it uses existing transfer learning methods on new data.
The researchers tackled cassava disease detection by applying transfer learning to a deep convolutional neural network on field images from Tanzania, achieving overall accuracy of 93% on unseen data and high accuracies (95-98%) for specific diseases and pest damages.
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.