The wood industry is facing many challenges. The high variability of raw material and the complexity of manufacturing processes results in a wide range of visible structure defects, which have to be controlled by trained specialists. These manual processes are not only tedious and biased, but also less effective. To overcome the drawbacks of the manual quality control processes, several automated vision-based systems have been proposed. Even though some conducted studies achieved a higher recognition rate than trained experts, researchers have to deal with a lack of large-scale databases and authentic data in this field. To address this issue, we performed a data acquisition experiment set in the industrial environment, where we were able to acquire an extensive set of authentic data from a production line. For this purpose, we designed and implemented a complex technical solution suitable for high-speed acquisition during harsh manufacturing conditions. In this data note, we present a large-scale dataset of high-resolution sawn timber surface images containing more than 43 000 labelled surface defects and covering 10 types of the most common wood defects. Moreover, with each image record, we provide two types of labels allowing researchers to perform semantic segmentation, as well as defect classification, and localization.

Department of Cybernetics and Biomedical Engineering VSB Technical University of Ostrava Ostrava 70800 Czech Republic

See more in PubMed

Broman O, Fredriksson M: Wood material features and technical defects that affect yield in a finger joint production process. Wood Material Science and Engineering. 2012;7(4):167–175. 10.1080/17480272.2012.699461 DOI

Ding F, Zhuang Z, Liu Y, et al. : Detecting Defects on Solid Wood Panels Based on an Improved SSD Algorithm. Sensors. 2020;20(18):5315. 10.3390/s20185315 PubMed DOI PMC

Projorov A: Great Soviet encyclopedia. 3rd ed. New York: Macmillan;1973.

Cetiner I, Var A, Cetiner H. 2014. Wood surface analysis with image processing techniques. 2014 22nd Signal Processing and Communications Applications Conference (SIU).

Gu I, Andersson H, Vicen R: Automatic Classification of Wood Defects Using Support Vector Machines. Computer Vision and Graphics. 2009;5337:356–367. 10.1007/978-3-642-02345-3_35 DOI

Urbonas A, Raudonis V, Maskeliūnas R, et al. : Automated Identification of Wood Veneer Surface Defects Using Faster Region-Based Convolutional Neural Network with Data Augmentation and Transfer Learning. Applied Sciences. 2019;9(22):4898. 10.3390/app9224898 DOI

Lycken A: Comparison between automatic and manual quality grading of sawn softwood. Forest Products Journal. 2006;56(4):13–18.

Liu Z, Peng C, Work T, et al. : Application of machine-learning methods in forest ecology: recent progress and future challenges. Environmental Reviews. 2018;26(4):339–350. 10.1139/er-2018-0034 DOI

Kryl M, Danys L, Jaros R, et al. : Wood Recognition and Quality Imaging Inspection Systems. Journal of Sensors. 2020;2020:1–19. 10.1155/2020/3217126 DOI

Shi J, Li Z, Zhu T, et al. : Defect Detection of Industry Wood Veneer Based on NAS and Multi-Channel Mask R-CNN. Sensors. 2020;20(16):4398. 10.3390/s20164398 PubMed DOI PMC

Fabijańska A, Danek M, Barniak J: Wood species automatic identification from wood core images with a residual convolutional neural network. Computers and Electronics in Agriculture. 2021;181:105941. 10.1016/j.compag.2020.105941 DOI

He T, Liu Y, Xu C, et al. : A Fully Convolutional Neural Network for Wood Defect Location and Identification. IEEE Access. 2019;7:123453–123462. 10.1109/ACCESS.2019.2937461 DOI

Gao M, Qi D, Mu H, et al. : A Transfer Residual Neural Network Based on ResNet-34 for Detection of Wood Knot Defects. Forests. 2021;12(2):212. 10.3390/f12020212 DOI

Jackson PTG, Amir AA, Bonner S, et al. : Style augmentation: data augmentation via style randomization. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019;6:10–11.

Baslerweb.com : Basler AG – Industriekamera Hersteller. [online].2022.[Accessed 12 June 2022]. https://www.baslerweb.com/en/antic-browser/?fbclid=IwAR3_dRxXgx-voXXpwLT5oh3qIHI0yMpGlQYUe4qbDSs4B_5VbtKTaT_uiuE

Kodytek P, Bodzas A: Supporting tools for managing and labeling raw wood defect images. Zenodo. 20 June 2022. https://zenodo.org/record/4864901#.YrDaMf1BzIV

Kodytek P, Bodzas A, Bilik P: Supporting data for Deep Learning and Machine Vision based approaches for automated wood defect detection and quality control. Zenodo. 20 June 2022. https://zenodo.org/record/4694695#.YrDZPf1BzIU

He K, Zhang X, Ren S, et al. : Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016.

Lin T, Maire M, Belongie S, et al. : Computer Vision – ECCV 2014. Common Objects in Context: Microsoft COCO.2014. 10.1007/978-3-319-10602-1_48 DOI

: Comparison of segmentation and identification of swietenia mahagoni wood defects with augmentation images. Heliyon .2021;7(6) : 10.1016/j.heliyon.2021.e07417 e07417 10.1016/j.heliyon.2021.e07417 PubMed DOI PMC