Version 1
: Received: 18 April 2024 / Approved: 19 April 2024 / Online: 19 April 2024 (10:38:00 CEST)
How to cite:
Chliveros, G.; Tzanetatos, I.; Kontomaris, S. V. Vessel Surface Corrosion Segmentation Approach Using a Decision-Tree Module for YOLO Trained Models. Preprints2024, 2024041320. https://doi.org/10.20944/preprints202404.1320.v1
Chliveros, G.; Tzanetatos, I.; Kontomaris, S. V. Vessel Surface Corrosion Segmentation Approach Using a Decision-Tree Module for YOLO Trained Models. Preprints 2024, 2024041320. https://doi.org/10.20944/preprints202404.1320.v1
Chliveros, G.; Tzanetatos, I.; Kontomaris, S. V. Vessel Surface Corrosion Segmentation Approach Using a Decision-Tree Module for YOLO Trained Models. Preprints2024, 2024041320. https://doi.org/10.20944/preprints202404.1320.v1
APA Style
Chliveros, G., Tzanetatos, I., & Kontomaris, S. V. (2024). Vessel Surface Corrosion Segmentation Approach Using a Decision-Tree Module for YOLO Trained Models. Preprints. https://doi.org/10.20944/preprints202404.1320.v1
Chicago/Turabian Style
Chliveros, G., Iason Tzanetatos and S. V. Kontomaris. 2024 "Vessel Surface Corrosion Segmentation Approach Using a Decision-Tree Module for YOLO Trained Models" Preprints. https://doi.org/10.20944/preprints202404.1320.v1
Abstract
In this paper we propose a module that uses features learned by a deep convolutional neural network to infer areas of corrosion and segment pixels to corrosion areas of inspection interest. Our segmentation module is based on eigen tree decomposition and information based decision criteria. To interrogate performance we use several state-of-the-art deep learning architectures and compare to our approach. The results indicate that our method produces better results in terms of accuracy and precision, whilst maintaining good (f-score) significance over the entire dataset.
Keywords
marine corrosion; corrosion detection; preventive monitoring; image segmentation; deep learning
Subject
Engineering, Marine Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.