DEVELOPMENT OF CROSS-CUTTING OPTIMIZING SCANNER FOR ASPEN AND BLACK ALDER BOARDS
DOI:
https://doi.org/10.68302/std2026.vol2.14Keywords:
Computer Vision, Deep Machine Learning, defect detection, FPGA, HPC, labelling, quality control, wood processingAbstract
In the paper, machine learning knowledge is transferred to wood processing industry. А universal Machine Learning system has great potential for the scalability in wood processing industry. In order to increase the yield of high-quality material and reduce the influence of subjective factors in the assessment of the quality of the wood boards, a machine learning model was trained as part of the research. The model was trained on a large set of aspen and black alder board samples, including subjective assessments of the acceptability. This approach ensures that the ML model is able to perceive and standardize different defect compositions that are considered to meet the specified quality requirements. As a result, a more accurate and consistent interpretation of wood defect recognition is achieved, significantly reducing the variation caused by the human factor along with proper feeding mechanism increase the yield of high-quality material. We proved that using ML for wood defect detection allowed to achieve a fully developed and sustainable defect recognition model within 3 months testing period. Identifying wood defects in the production of aspen and black alder boards is both a technologically complex and subjectively influenced process. By combining the assessment of defect intensity, area, structure and location, the model ensures a uniform quality standard throughout production. This reduces unjustified board rejection, improves material utilisation rate and promotes a more stable output of high-quality material.
Supporting Agencies
Development of cross-cutting optimizing scanner for aspen and black alder boards. Research contract Nr: DP09 signed between SIA LV Timber and Forest Sector Competence Center of Latvia. The research results have been co-financed by the European Union, and carried out in cooperation with Forest Sector Competence Center of Latvia. Project number DP09, co-financing agreement number 2.2.1.3.i.0/1/24/A/CFLA/001.Downloads
References
[1] Central Statistical Database, “Production, exports and imports of wood products by Indicator.” [Online]. Available: https://data.stat.gov.https//data.stat.gov.lv/api/v1/en/OSP_PUB/START/NOZ/ME/MEK/MEK010
[2] Investment and Development Agency of Latvia, “Woodworking.” [Online]. Available: https://investinlatvia.org/assets/upload/woodworking_2022_LIAA.pdf
[3] B. R. Hartanto, T. Ma, Y. Kurata, H. Kobori, S. Tsuchikawa, and T. Inagaki, “Integrating image analysis and ensemble learning for predictive modeling of wood density and MC using line scanner and camera systems,” Inf. Process. Agric., Dec. 2025, doi: 10.1016/j.inpa.2025.11.008.
[4] S.-W. Hwang and J. Sugiyama, “Computer vision-based wood identification and its expansion and contribution potentials in wood science: A review,” Plant Methods, vol. 17, no. 1, p. 47, Apr. 2021, doi: 10.1186/s13007-021-00746-1.
[5] H. Wang, G. Zhang, and H. Qi, “Wood Recognition Using Image Texture Features,” PLoS One, vol. 8, no. 10, p. e76101, Oct. 2013, doi: 10.1371/journal.pone.0076101.
[6] T. He, S. Mu, H. Zhou, and J. Hu, “Wood species identification based on an ensemble of deep convolution neural networks,” Wood Res., vol. 66, no. 1, pp. 01–14, Mar. 2021, doi: 10.37763/wr.1336-4561/66.1.0114.
[7] K. Forghani, M. Carlsson, P. Flener, M. Fredriksson, J. Pearson, and D. Yuan, “Maximizing value yield in wood industry through flexible sawing and product grading based on wane and log shape,” Comput. Electron. Agric., vol. 216, p. 108513, Jan. 2024, doi: 10.1016/j.compag.2023.108513.
[8] S. M. Hosseini and A. Peer, “Wood Products Manufacturing Optimization: A Survey,” IEEE Access, vol. 10, pp. 121653–121683, 2022, doi: 10.1109/ACCESS.2022.3223053.
[9] S. M. Bhandarkar, T. D. Faust, and M. Tang, “Design and prototype development of a computer vision-based lumber production planning system,” Image Vis. Comput., vol. 20, no. 3, pp. 167–189, Mar. 2002, doi: 10.1016/S0262-8856(01)00087-7.
[10] T. Gergeľ, M. Sedliak, T. Bucha, M. Oravec, M. Slamka, and M. Pástor, “Prediction Model of Wooden Logs Cutting Patterns and Its Efficiency in Practice,” Appl. Sci., vol. 10, no. 9, p. 3003, Apr. 2020, doi: 10.3390/app10093003.
[11] J. L. A. Parra Galvez, D. Borenstein, and E. da Silveira Farias, “Application of optimization for solving a sawing stock problem with a cant sawing pattern,” Optim. Lett., vol. 12, no. 8, pp. 1755–1772, Dec. 2018, doi: 10.1007/s11590-017-1178-x.
[12] A. Silva, L. C. Coelho, M. Darvish, and J. Renaud, “A cutting plane method and a parallel algorithm for packing rectangles in a circular container,” Eur. J. Oper. Res., vol. 303, no. 1, pp. 114–128, Nov. 2022, doi: 10.1016/j.ejor.2022.02.023.
[13] F. de Miguel-Díez et al., “Further application of using a personal laser scanner and simultaneous localization and mapping technology to estimate the log’s volume and its comparison with traditional methods,” Int. J. Appl. Earth Obs. Geoinf., vol. 109, p. 102779, May 2022, doi: 10.1016/j.jag.2022.102779.
[14] D. M. Drew, G. M. Downes, T. Seifert, A. Eckes-Shepard, and A. Achim, “A Review of Progress and Applications in Wood Quality Modelling,” Curr. For. Reports, vol. 8, no. 4, pp. 317–332, Aug. 2022, doi: 10.1007/s40725-022-00171-0.
[15] N. Cattaneo, S. Puliti, C. Fischer, and R. Astrup, “Estimating wood quality attributes from dense airborne LiDAR point clouds,” For. Ecosyst., vol. 11, p. 100184, 2024, doi: 10.1016/j.fecs.2024.100184.
[16] O. Abdeljaber and A. Olsson, “Cross-sectional analysis of timber boards using convolutional long short-term memory neural networks,” Constr. Build. Mater., vol. 451, p. 138855, Nov. 2024, doi: 10.1016/j.conbuildmat.2024.138855.
[17] L. Wu, F. Morosi, and G. Caruso, “The development of a low-cost photometric-stereo-based material scanner,” HardwareX, vol. 25, p. e00740, Mar. 2026, doi: 10.1016/j.ohx.2025.e00740.
[18] W. Zeng, T. Inagaki, S. Tsuchikawa, G. Schajer, L. Gao, and T. Ma, “Enabling moisture monitoring and deformation analysis in wood during drying by 4D-CT imaging coupled with deep learning,” Ind. Crops Prod., vol. 241, p. 122729, Mar. 2026, doi: 10.1016/j.indcrop.2026.122729.
[19] C. Marc, B. Marcon, L. Denaud, and S. Girardon, “FMCW THZ radar and X-ray analysis of wood properties: A comparative study,” NDT E Int., vol. 154, p. 103378, Sep. 2025, doi: 10.1016/j.ndteint.2025.103378.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Vladimirs Šatrevičs, Māris Asafrejs, Viktorija Skvarciany, Inga Eriņa
This work is licensed under a Creative Commons Attribution 4.0 International License.
