Abstract
Automatic species identification has the potential to improve the efficacy and automation of wood processing systems significantly. Recent advances in deep learning allowed for the automation of many previously difficult tasks, and in this paper, we investigate the feasibility of using deep convolutional neural networks (CNNs) for hardwood lumber identification. In particular, two highly effective CNNs (ResNet-50 and DenseNet-121) as well as lightweight MobileNet-V2 were tested. Overall, 98.2% accuracy was achieved for 11 common hardwood species classification tasks.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Alfonso V, Baas P, Carlquist S, Chimelo J, Coradin V, Détienne P, Gasson P, Grosser D, Ilic J, Kuroda K, Miller R, Ogata K, Richter H, Welle B, Wheeler E (1989) Iawa list of microscopic features for hardwood identification: with an appendix on non-anatomical information. IAWA J 10:221–358. https://doi.org/10.1163/22941932-90000496
Gazo R, Wells L, Krs V, Benes B (2018) Validation of automated hardwood lumber grading system. Comput Electron Agric 155:496–500. https://doi.org/10.1016/j.compag.2018.06.041
Geirhos R, Rubisch P, Michaelis C, Bethge M, Wichmann FA, Brendel W (2019) IImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In: Proc. 6th Int. Conf. Learn. Represent. https://openreview.net/forum?id=Bygh9j09KX
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press, Cambridge
Haralick RM, Shanmugam K, Dinstein IH (1973) Textural features for image classification. IEEE Trans Syst Man Cybern Syst SMC 3(6):610–621. https://doi.org/10.1109/TSMC.1973.4309314
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp 770–778. https://doi.org/10.1109/CVPR.2016.90
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp 4700–4708 https://doi.org/10.1109/CVPR.2017.243
Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proc. 32nd Int. Conf. Mach. Learn., pp 448–456
Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. In: Proc. 3rd Int. Conf. Learn. Represent
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324. https://doi.org/10.1109/5.726791
Martins J, Oliveira L, Nisgoski S, Sabourin R (2013) A database for automatic classification of forest species. Mach Vis Appl 24(3):567–578. https://doi.org/10.1007/s00138-012-0417-5
Ojala T, Pietikäinen M, Harwood D (1996) A comparative study of texture measures with classification based on featured distributions. Pattern Recognit 29(1):51–59. https://doi.org/10.1016/0031-3203(95)00067-4
Olshausen BA, Field DJ (1996) Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583):607–609. https://doi.org/10.1038/381607a0
Paula Filho PL, Oliveira LS, Nisgoski S, Britto AS (2014) Forest species recognition using macroscopic images. Mach Vis Appl 25(4):1019–1031. https://doi.org/10.1007/s00138-014-0592-7
Ravindran P, Costa A, Soares R, Wiedenhoeft AC (2018) Classification of cites-listed and other neotropical meliaceae wood images using convolutional neural networks. Plant methods 14(1):25
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp 4510–4520. https://doi.org/10.1109/CVPR.2018.00474
Settle J, Gonso C (2020) 2020 Indiana forest products price report and trend analysis. Tech. rep, Indiana Department of Natural Resources. https://www.in.gov/dnr/forestry/files/fo-spring-price-report-2020.pdf
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Technol 15(1):1929–1958
Stone M (1974) Cross-validatory choice and assessment of statistical predictions. J R Stat Soc Series B Stat Methodol 36(2):111–133
Wells L, Gazo R, Del Re R, Krs V, Benes B (2018) Defect detection performance of automated hardwood lumber grading system. Comput Electron Agric 155:487–495. https://doi.org/10.1016/j.compag.2018.09.025
Acknowledgements
This research was supported by the Foundation for Food and Agriculture Research Grant ID: 602757 to Benes and McIntire Stennis grant accession no. 1012928 to Gazo from the USDA National Institute of Food and Agriculture. The content of this publication is solely the responsibility of the authors and does not necessarily represent the official views of the respective funding agencies.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wu, F., Gazo, R., Haviarova, E. et al. Wood identification based on longitudinal section images by using deep learning. Wood Sci Technol 55, 553–563 (2021). https://doi.org/10.1007/s00226-021-01261-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00226-021-01261-1