Detection of Knots in Oak Wood Planks: Instance Versus Semantic Segmentation

2022 IEEE 5th International Conference on Big Data and Artificial Intelligence (BDAI 2022): Proceedings 2022
Ēvalds Urtāns, Kārlis Būmanis, Valters Vēciņš, Māris Ancāns, Aiga Andrijanova, Mārcis Teodors Upenieks, Kristofers Volkovs

In this study, we present a new dataset of knotcovered oak planks. It contains 1500 images that have 1 to 11 knots per image, along with mask and bounding-box annotations. The data set was evaluated using deep machine learning methods, and it has been found that instance segmentation models are superior in this task, achieving 59% Box-IoU versus 49% Box-IoU using semantic segmentation. Instance segmentation performed better to detect knots by segmenting instances with an accuracy of 90%, while semantic segmentation detected konts with an accuracy of 89%.

Atslēgas vārdi
wood surface defects, wood industry, wood processing, wood quality control process, wood defects dataset, instance segmentation, semantic segmentation, deep learning, dataset
DOI
10.1109/BDAI56143.2022.9862633
Hipersaite
https://ieeexplore.ieee.org/document/9862633

Urtāns, Ē., Būmanis, K., Vēciņš, V., Ancāns, M., Andrijanova, A., Upenieks, M., Volkovs, K. Detection of Knots in Oak Wood Planks: Instance Versus Semantic Segmentation. No: 2022 IEEE 5th International Conference on Big Data and Artificial Intelligence (BDAI 2022): Proceedings, Ķīna, Fuzhou, 8.-10. jūlijs, 2022. Piscataway: IEEE, 2022, 163.-168.lpp. ISBN 978-1-6654-7082-7. e-ISBN 978-1-6654-7081-0. Pieejams: doi:10.1109/BDAI56143.2022.9862633

Publikācijas valoda
English (en)