Segmentation of plywood veneers as a pre-processing step in image analysis for material quality assessment
Resumo
The aesthetic quality of wood veneers is a decisive factor in adding value to the industry. Manual inspection presents limitations such as subjectivity and fatigue, motivating the use of Computer Vision. This study presents an approach to segment the veneer region in images collected in a real environment, aiming to adequately identify the area of interest for subsequent material quality classification. A YOLOv8 model trained for this purpose achieved a mAP@50 of 0.995 on the experimental database composed of 106 annotated images. Additionally, the model was qualitatively evaluated on 1,000 unlabeled images acquired under real operating conditions, yielding consistent, visually coherent segmentation results.
Referências
Hoang, V. T., Le, V.-T., Dinh, N., Tran-Trung, K., Van, B. N., Hong, H. D. T., and Huong, T. H. (2025). Deep Learning-based faulty wood detection with area attention. Computers, Materials & Continua, 85(1).
Kang, C. H. and Kim, S. Y. (2023). Real-time object detection and segmentation technology: an analysis of the yolo algorithm. JMST Advances, 5(2):69–76.
Long, J., Shelhamer, E., and Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3431–3440.
Nguyen-Trong, K. (2023). Evaluation of wood species identification using CNN-based networks at different magnification levels. International Journal of Advanced Computer Science and Applications, 14(4).
Ramos-Maldonado, M., Gutiérrez, F., Gallardo-Venegas, R., Bustos-Avila, C., Contreras, E., and Lagos, L. (2025). Machine learning and industrial data for veneer quality optimization in plywood manufacturing. Processes, 13(4):1229.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779–788.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer.
Sapkota, R. and Karkee, M. (2025). Ultralytics yolo evolution: An overview of yolo26, yolo11, yolov8 and yolov5 object detectors for computer vision and pattern recognition. arXiv preprint arXiv:2510.09653.
Wang, R., Chen, Y., Liang, F., Wang, B., Mou, X., and Zhang, G. (2024). Bpn-yolo: a novel method for wood defect detection based on YOLOv7. Forests, 15(7):1096.
Yi, L. P., Akbar, M. F., Ab Wahab, M. N., Rosdi, B. A., Fauthan, M. A., and Shrifan, N. H. (2024). The prospect of Artificial Intelligence-based wood surface inspection: A review. IEEE Access, 12:84706–84725.
Kang, C. H. and Kim, S. Y. (2023). Real-time object detection and segmentation technology: an analysis of the yolo algorithm. JMST Advances, 5(2):69–76.
Long, J., Shelhamer, E., and Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3431–3440.
Nguyen-Trong, K. (2023). Evaluation of wood species identification using CNN-based networks at different magnification levels. International Journal of Advanced Computer Science and Applications, 14(4).
Ramos-Maldonado, M., Gutiérrez, F., Gallardo-Venegas, R., Bustos-Avila, C., Contreras, E., and Lagos, L. (2025). Machine learning and industrial data for veneer quality optimization in plywood manufacturing. Processes, 13(4):1229.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779–788.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer.
Sapkota, R. and Karkee, M. (2025). Ultralytics yolo evolution: An overview of yolo26, yolo11, yolov8 and yolov5 object detectors for computer vision and pattern recognition. arXiv preprint arXiv:2510.09653.
Wang, R., Chen, Y., Liang, F., Wang, B., Mou, X., and Zhang, G. (2024). Bpn-yolo: a novel method for wood defect detection based on YOLOv7. Forests, 15(7):1096.
Yi, L. P., Akbar, M. F., Ab Wahab, M. N., Rosdi, B. A., Fauthan, M. A., and Shrifan, N. H. (2024). The prospect of Artificial Intelligence-based wood surface inspection: A review. IEEE Access, 12:84706–84725.
Publicado
22/04/2026
Como Citar
GOTARDO, Cristian; MARINI, Andreia; ORTONCELLI, André Roberto.
Segmentation of plywood veneers as a pre-processing step in image analysis for material quality assessment. In: ESCOLA REGIONAL DE BANCO DE DADOS (ERBD), 21. , 2026, Dois Vizinhos/PR.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 153-156.
ISSN 2595-413X.
DOI: https://doi.org/10.5753/erbd.2026.20338.
