The present work shows the application of transfer learning for a pre-trained deep neural network (DNN), using a small image dataset (≈ 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.
@article{arxiv.1802.00030,
title = {Fusarium Damaged Kernels Detection Using Transfer Learning on Deep Neural Network Architecture},
author = {Márcio Nicolau and Márcia Barrocas Moreira Pimentel and Casiane Salete Tibola and José Mauricio Cunha Fernandes and Willingthon Pavan},
journal= {arXiv preprint arXiv:1802.00030},
year = {2018}
}