To ensure flight safety of aircraft structures, it is necessary to have regular maintenance using visual and nondestructive inspection (NDI) methods. In this paper, we propose an automatic image-based aircraft defect detection using Deep Neural Networks (DNNs). To the best of our knowledge, this is the first work for aircraft defect detection using DNNs. We perform a comprehensive evaluation of state-of-the-art feature descriptors and show that the best performance is achieved by vgg-f DNN as feature extractor with a linear SVM classifier. To reduce the processing time, we propose to apply SURF key point detector to identify defect patch candidates. Our experiment results suggest that we can achieve over 96% accuracy at around 15s processing time for a high-resolution (20-megapixel) image on a laptop.
@article{arxiv.1712.09213,
title = {Aircraft Fuselage Defect Detection using Deep Neural Networks},
author = {Touba Malekzadeh and Milad Abdollahzadeh and Hossein Nejati and Ngai-Man Cheung},
journal= {arXiv preprint arXiv:1712.09213},
year = {2020}
}