Fusarium Damaged Kernels Detection Using Transfer Learning on Deep Neural Network Architecture
This work addresses the need for efficient and equipment-independent detection of Fusarium head blight symptoms in wheat, though it is incremental as it applies existing transfer learning methods to a specific agricultural domain.
The researchers tackled the problem of detecting Fusarium damaged kernels in wheat by applying transfer learning on a pre-trained deep neural network, achieving an overall average accuracy of 94.7% with a 20% misclassification rate on an external test dataset.
The present work shows the application of transfer learning for a pre-trained deep neural network (DNN), using a small image dataset ($\approx$ 12,000) on a single workstation with enabled NVIDIA GPU card that takes up to 1 hour to complete the training task and archive an overall average accuracy of $94.7\%$. The DNN presents a $20\%$ score of misclassification for an external test dataset. The accuracy of the proposed methodology is equivalent to ones using HSI methodology $(81\%-91\%)$ used for the same task, but with the advantage of being independent on special equipment to classify wheat kernel for FHB symptoms.