Deep Learning Method of Precious Wood Image Classification Based on Microscopic Computed Tomography
Source abstract
Abstract
Correctly identifying precious wood species is crucial for import and export trade and furniture material identification. This study utilizes nondestructive testing (microscopic computed tomography, Micro-CT) to capture microscopic images of the transverse, radial, and tangential sections of 24 precious wood species, creating a comprehensive dataset. The SLConNet deep learning model is developed, enhancing recognition accuracy through multi-scale convolution and an improved residual block structure. The experiment results show that the classification accuracy of the transverse, radial and tangential sections is 98.72, 96.75, and 95.36%, respectively, when the gain value is 0.8. The model outperforms traditional models like Alexnet, ResNet50, Inception-V3, and Xception. This research highlights the efficiency of nondestructive testing in obtaining a large number of microscopic wood images, compared to traditional anatomical methods. The SLConNet model showcases high accuracy in precision, recall, and specificity, suggesting its potential for widespread applications in wood classification.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Wood and Agarwood Research · Remote Sensing and LiDAR Applications · Image Processing and 3D Reconstruction
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (47)
Show source-provided references
1. Huang, W., Li, H. Q., Guan, H., et al., Advances in functionalization and application of natural woods, Mater. Rep., 2022, vol. 36, no. 18, pp. 224–230.
2. Amini, M. H. M., Temiz, A., Hekimolu, G., et al., Properties of scots pine wood impregnated with capric acid for potential energy saving building material, Holzforschung, 2022, vol. 76, no. 8, p. 1.
3. Rojas, J. A. M., Alpuente, J., Postigo, D., Rojas, I. M., and Vignote, S., Wood species identification using stress–wave analysis in the audible range, Appl. Acoust., 2011, vol. 72, no. 12, pp. 934–942.10.1016/j.apacoust.2011.05.016 ↗
4. Jiao, L., Lu, Y., He, T., Guo, J., and Yin, Y., DNA barcoding for wood identification: global review of the last decade and future perspective, IAWA J., 2020, vol. 41, no. 4, pp. 620–643.10.1163/22941932-bja10041 ↗
5. Wang, C.K. and Zhao, P., Classification of wood species using spectral and texture features of transverse section, Eur. J. Wood Wood Prod., 2021, vol. 79, pp. 1283–1296.10.1007/s00107-021-01728-9 ↗
6. Creydt, M., Lautner, S., Fromm, J., et al., Wood profiling by non-targeted liquid chromatography high-resolution mass spectrometry: Part 2, Detection of the geographical origin of spruce wood (Piceaabies) by determination of metabolite pattern, J. Chromatogr., 2021, vol. 1663, p. 462737.10.1016/j.chroma.2021.462737 ↗
7. Jiao, L., Yu, M., Wiedenhoeft, A.C., et al., DNA barcode authentication and library development for the wood of six commercial Pterocarpus species: the critical role of xylarium specimens, Sci. Rep., 2018, no. 8, p. 1945.10.1038/s41598-018-20381-6 ↗
8. Sun, X.D., Cui, D.D., Shen, Y., et al., Nondestructive detection for foreign bodies of tea stalks in finished tea products using terahertz spectroscopy and imaging, Infrared Phys. Technol., 2022, no. 121, p. 04018.10.1016/j.infrared.2021.104018 ↗
9. Helmling, S., Olbrich, A., Heinz, I., et al., Atlas of vessel elements, IAWA J., 2018, vol. 39, no. 3, pp. 249–352.10.1163/22941932-20180202 ↗
10. Santosa, S., Pramunendar, R.A., Prabowo, D.P., et al., Wood types classification using back-propagation neural network based on genetic algorithm with gray level co-occurrence matrix for features extraction, IAENG Int. J. Comput. Sci., 2019, vol. 46, pp. 149–155.
11. Khalil, R. A., Jones, E., Babar, M. I., et al., Speech emotion recognition using deep learning techniques: A review, IEEE Access, 2019, vol. 99, p. 1.
12. Huang, J.X., Lu, X., Chen, L.Y., et al., Accurate identification of pine wood nematode disease with a deep convolution neural network, Remote Sens., 2022, vol. 14, p. 913.10.3390/rs14040913 ↗
13. IAWA Committee, IAWA list of microscopic features for softwood identification, IAWA J., 2004, vol. 25, no. 1, pp. 1–70.10.1163/22941932-90000349 ↗
14. Wheeler, E.A., Baas, P., Gasson, P.E., et al., IAWA list of microscopic features for hardwood identification, IAWA J., 1989, vol. 10, no. 3, pp. 219–332.10.1163/22941932-90000496 ↗
15. Helmling, S., Olbrich, A., Heinz, I., et al., Atlas of vessel elements, IAWA J., 2018, vol. 39, no. 3, pp. 249–352.10.1163/22941932-20180202 ↗
16. Song, L.H., Lei, F.J., Huang, Y.H., et al., Anatomical properties of melia azedarach and toona sinensis woods, Guangxi For. Sci., 2023, vol. 52, no. 6, pp. 781–786.
17. Liu, S.J., He, T., Lu, Y., et al., Quantitative anatomy analysis on wood feature variability and wood identification of Swietenia species, Sci. Silvae Sin., pp. 1–11.
18. Guo, J.X. and Hu, M., Features extraction and classification of wood defect based on hu invariant moment and wavelet moment and BP neural network, Proc. 12th Int. Symp. Visual Inf. Commun. Interact. (VINCI’19) (New York, 2019).
19. Riana, D., Rahayu, S., and Hasan, M., Comparison of segmentation and identification of Swietenia mahagoni wood defects with augmentation images, Heliyon, 2021, vol. 7, no. 6, p. 7417.10.1016/j.heliyon.2021.e07417 ↗
20. Yang, X.X., Gao, Y.S., and Zhang, S.H., Research on rosewood micro image classification method based on feature fusion and ELM, J. Renew. Mater., 2022, vol. 10, no. 12, pp. 3587–3598.10.32604/jrm.2022.022300 ↗
21. Barmpoutis, P., Dimitropoulos, K., Barboutis, I., et al., Wood species recognition through multidimensional texture analysis, Comput. Electron. Agric., 2018, vol. 144, pp. 241–248.10.1016/j.compag.2017.12.011 ↗
22. Chao, X.F., Fan, L.H., Cai, C., et al., Wood texture classification and identification based on multi–feature extraction and selection, Mod. Agric. Sci., 2018, no. 18, pp. 118–120.
23. Rosa da Silva, N., De Ridder, M., Baetens, J.M., Van den Bulcke, J., Rousseau, M., et al., Automated classification of wood transverse cross-section micro-imagery from 77 commercial Central-African timber species, Ann. For. Sci., 2017, vol. 74, no. 2, p. 30.10.1007/s13595-017-0619-0 ↗
24. Barmpoutis, P., Dimitropoulos, K., Barboutis, I., Grammalidis, N., and Lefakis, P., Wood species recognition through multidimensional texture analysis, Comput. Electron. Agric., 2018, vol. 144, pp. 241–248.10.1016/j.compag.2017.12.011 ↗
25. Yusof, R.A., Ahmad, A.B., and Khairuddin, A.S.M.C., Transfer learning approach in automatic tropical wood recognition system, Comput. Exp. Simul. Eng., 2020, vol. 75, pp. 1225–1233.10.1007/978-3-030-27053-7_104 ↗
26. Zhao, P., Han, J.C., and Wang, C.K., Classification of wood species using hyperspectral microscopic imaging based on I-BGLAM texture and spectral fusion, Spectrosc. Spect. Anal., 2021, vol. 41, no. 2, pp. 599–605.
27. Bruno, O., Ribas, L., Condori, R. M., Scabini, L. S., Bruno, O., Ribas, L., et al., Evaluating deep convolutional neural networks as texture feature extractors, Int. Conf. Image Anal. Process. (2019).
28. Fabijańska, A., Danek, M., and Barniak, J., Wood species automatic identification from wood core images with a residual convolutional neural network, Comput. Electron. Agric., 2021, vol. 181, p. 105941.10.1016/j.compag.2020.105941 ↗
29. Wang, Y., Zhang, W., Gao, R., Jin, Z., and Wang, X.H., Recent advances in the application of deep learning methods to forestry, Wood Sci. Technol., 2021, vol. 55, no. 5, pp. 1171–1202.10.1007/s00226-021-01309-2 ↗
30. Chen, L. X., Ge, Z. D., Luo, R., et al., Identification of CT image defects in wood based on convolution neural network, Sci. Silvae Sin., 2018, vol. 54, no. 11, pp. 127–133.
31. Wang, H., Li, Z., and Zou, X., Wood surface defect detection based on adaboost and CNN, J. Syst. Simul., 2019, vol. 31, no. 8, pp. 1636–1645.
32. Shi, J., Li, Z., Zhu, T., Wang, D., and Ni, C., Defect detection of industry wood veneer based on NAS and multi-channel mask R-CNN, Sensors, 2020, vol. 20, no. 16, p. 4398.10.3390/s20164398 ↗
33. Yusof, R. A., Ahmad, A. B., Khairuddin, A.S.M.C., Transfer learning approach in automatic tropical wood recognition system, Computational and Experimental Simulations in Engineering, 2020, vol. 75, pp. 1225–1233.10.1007/978-3-030-27053-7_104 ↗
34. Wu, F., Gazo, R., Haviarova, E., Benes, B., Wood identification based on longitudinal section images by using deep learning, Wood Science and Technology, 2021, vol. 55, no. 2, pp. 553–563.10.1007/s00226-021-01261-1 ↗
35. Ravindran, P., Costa, A., Soares, R.,Wiedenhoeft, A. C., Classification of CITES-listed and other neotropical Meliaceae wood images using convolutional neural networks, Plant Methods, 2018, vol. 14, no. 1, p. 25.10.1186/s13007-018-0292-9 ↗
36. Briechle, S., Krzystek, P., Vosselman, G., Silvi-Net-A dual-CNN approach for combined classification of tree species and standing dead trees from remote sensing data, International Journal of Applied Earth Observation and Geoinformation, vol. 98, p. 102292.10.1016/j.jag.2020.102292 ↗
37. Verly Lopes, D. J., Burgreen, G. W., Entsminger, E. D., North American hardwoods identification using machine-learning, Forests, 2020, vol. 11, no. 3, p. 298.10.3390/f11030298 ↗
38. Wu, F., Gazo, R., Haviarova, E., and Benes, B., Wood identification based on longitudinal section images by using deep learning, Wood Sci. Technol., 2021, vol. 55, no. 2, pp. 553–563.10.1007/s00226-021-01261-1 ↗
39. Zhao, Z.Y., Yang, X.X., Ge, Z.D., and Zhou, Y.C., Wood microscopic image identification method based on convolution neural network, BioResources, 2021, vol. 16, no. 3, pp. 4986–4999.10.15376/biores.16.3.4986-4999 ↗
40. Kita, Y. and Sugiyama, J.J., Wood identification of two anatomically similar cupressaceae species based on two-dimensional microfibril angle mapping, Holzforschung, 2021, vol. 75, no. 7, pp. 591–602.10.1515/hf-2020-0079 ↗
41. Shanthi, T. and Sabeenian, R.S., Modified Alexnet architecture for classification of diabetic retinopathy images, Comput. Electr. Eng., 2019, vol. 76, pp. 56–64.10.1016/j.compeleceng.2019.03.004 ↗
42. Unnikrishnan, A., Sowmya, V., and Soman, K.P., Deep AlexNet with reduced number of trainable parameters for satellite image classification, Proc. Comput. Sci., 2018, vol. 143, pp. 931–938.
43. Paisitkriangkrai, S., Shen, C., and Anton, V.D.H., Learning to rank in person re-identification with metric ensembles, IEEE Conf. Comput. Vision Pattern Recognit. (CVPR) (2015).10.1109/CVPR.2015.7298794 ↗
44. Arredondo, J.R.P., Tanscheit, R., Monteiro, E.C., da Silva, E.C., and de Sousa, I.P., Classification of mechanisms underlying cardiac arrhythmias by deep learning, Res. Biomed. Eng., 2020, vol. 36, no. 4, pp. 475–487.10.1007/s42600-020-00085-5 ↗
45. Polat, Z., Detection of Covid-19 from chest CT images using Xception architecture: A deep transfer learning-based approach, Sakarya Univ. J. Sci., 2021, vol. 25, no. 3, pp. 813–823.
46. Feng, B., Liu, Y., Chi, H., and Chen, X.Z., Hyperspectral remote sensing image classification based on residual generative adversarial neural networks, Signal Process., 2023, vol. 213, no. 9, p. 109202.10.1016/j.sigpro.2023.109202 ↗
47. Yao, Q.Y., Zhang, L.M., Zheng, W.G., and Zhou, Y.X., Multi-scale SE-residual network with transformer encoder for myocardial infarction classification, Appl. Soft. Comput., 2023, vol. 149, p. 110919.10.1016/j.asoc.2023.110919 ↗