Abstract
Digital image processing has been widely used in the wood industry, and it is expected that the algorithms are accurate and have low computational complexities, especially for the real-time lumber grading and lumber classification processes. This paper investigates variations of deep learning strategies based on ResNet18 for classification of lumber images. The four datasets used in this work were manually marked as lumber defects, wood textures and lumbers by experts. A key ideal is to employ the transfer learning in the context of convolutional neural networks with a classifier layer only training with a small amount of training data for different tasks at the same lumber machinery. Through the expansion of unbalanced samples, the accuracy rate has been effectively improved. The human involvement when needed is kept to a minimum only for the training phase. The proposed approach was independently tested with four datasets, of which 80% of the data is used for training and 20% of the data is used for testing. The classification accuracy of the approach for each of the datasets is 98.16%, 93.32%, 96.64% and 99.50%. The average time for sorting the lumber image was kept at 0.003 s when the system runs on Nvidia GTX860 GPU.
Similar content being viewed by others
References
Arivazhagan S, Ganesan L (2003) Texture classification using wavelet transform. Elsevier Science Inc, Amsterdam. https://doi.org/10.1016/s0167-8655(02)00390-2
Bai X, Wang K, Hui W (2005) Research on the classification of wood texture based on gray level co-occurrence matrix. J Harbin Inst Technol 37(12):1667–1670. https://doi.org/10.3321/j.issn:0367-6234.2005.12.022
Canziani A, Paszke A, Culurciello E (2016) An analysis of deep neural network models for practical applications. arXiv:1605.07678
Cetiner S, Var AA, Cetiner H (2017) Classification of KNOT defect types. In: Signal processing and communications applications conference. IEEE. https://doi.org/10.5755/j01.eie.22.6.17227
Estevez PA, Perez CA, Goles E (2003) Genetic input selection to a neural classifier for defect classification of radiata pine boards. For Prod J 53(7):87–94
Gu IYH, Andersson H, Vicen R (2010) Wood defect classification based on image analysis and support vector machines. Wood Sci Technol 44:693–704. https://doi.org/10.1007/s00226-009-0287-9
He K, Zhang X, Ren S (2016) Deep residual learning for image recognition. https://doi.org/10.1109/cvpr.2016.90
Ibrahim I, Mohd Khairuddin AS, Abu Talip MS (2017) Tree species recognition system based on macroscopic image analysis. Wood Sci Technol 51:431–444. https://doi.org/10.1007/s00226-016-0859-4
Khalid M, Lew YL, Yusof R, Nadaraj M (2008) Design of an intelligent wood species recognition system. Int J Simul Syst Sci Technol 9(3):9–19
Laina I, Rupprecht C, Belagiannis V (2016) Deeper depth prediction with fully convolutional residual networks. https://doi.org/10.1109/3dv.2016.32
Mahram A (2012) Classification of wood surface defects with hybrid usage of statistical and textural features. In: International conference on telecommunications and signal processing. IEEE. https://doi.org/10.1109/tsp.2012.6256397
Mu H, Zhang M, Qi D, Guan S, Ni H (2015) Wood defects recognition based on fuzzy bp neural network. Int J Smart Home 9(5):143–152. https://doi.org/10.14257/ijsh.2015.9.5.14
Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: International conference on neural information processing systems. https://doi.org/10.1109/tpami.2016.2577031
Ruz GA, Pablo AE, Pablo AR (2009) Automated visual inspection system for wood defect classification using computational intelligence techniques. Int J Syst Sci 40(2):10. https://doi.org/10.1080/00207720802630685
Simard PY, Steinkraus D, Platt JC (2003) Best practices for convolutional neural networks applied to visual document analysis. IEEE Comput Soc. https://doi.org/10.1109/icdar.2003.1227801
Tou JY, Tay YH, Lau PY (2009) A comparative study for texture classification techniques on wood species recognition problem. In: International conference on natural computation. IEEE. https://doi.org/10.1109/icnc.2009.594
Yusof R, Khalid M, Khairuddin ASM (2013a) Application of kernel-genetic algorithm as nonlinear feature selection in tropical wood species recognition system. Comput Electron Agric 93(2):68–77. https://doi.org/10.1016/j.compag.2013.01.007
Yusof R, Khalid M, Khairuddin ASM (2013b) Fuzzy logic-based pre-classifier for tropical wood species recognition system. Mach Vis Appl 24:1589–1604. https://doi.org/10.1007/s00138-013-0526-9
Acknowledgements
This work was supported by the Fundamental Research Funds for the Central Universities (Nos. 2572015BB11, 2572017CB10), Heilongjiang Provincial Postdoctoral Science Foundation (Nos. LBH-Z16006, LBH-Z16011) and Program of National Natural Science of China (No. 31670721).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
On behalf of all authors, the corresponding author states that there is 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
Hu, J., Song, W., Zhang, W. et al. Deep learning for use in lumber classification tasks. Wood Sci Technol 53, 505–517 (2019). https://doi.org/10.1007/s00226-019-01086-z
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00226-019-01086-z