Journal of the Korean Wood Science and Technology

The Korean Society of Wood Science & Technology (한국목재공학회)
권호 표지
DOI QR코드

DOI QR Code

Mask Region-Based Convolutional Neural Network (R-CNN) Based Image Segmentation of Rays in Softwoods

  • Hye-Ji, YOO (Department of Forest Products, Chungbuk National University) ;
  • Ohkyung, KWON (National Instrumentation Center for Environmental Management, Seoul National University) ;
  • Jeong-Wook, SEO (Department of Wood and Paper Science, Chungbuk National University)
  • Received : 2022.10.16
  • Accepted : 2022.11.18
  • Published : 2022.11.25
Download PDF
⟨ Previous Next ⟩

Abstract

The current study aimed to verify the image segmentation ability of rays in tangential thin sections of conifers using artificial intelligence technology. The applied model was Mask region-based convolutional neural network (Mask R-CNN) and softwoods (viz. Picea jezoensis, Larix gmelinii, Abies nephrolepis, Abies koreana, Ginkgo biloba, Taxus cuspidata, Cryptomeria japonica, Cedrus deodara, Pinus koraiensis) were selected for the study. To take digital pictures, thin sections of thickness 10-15 ㎛ were cut using a microtome, and then stained using a 1:1 mixture of 0.5% astra blue and 1% safranin. In the digital images, rays were selected as detection objects, and Computer Vision Annotation Tool was used to annotate the rays in the training images taken from the tangential sections of the woods. The performance of the Mask R-CNN applied to select rays was as high as 0.837 mean average precision and saving the time more than half of that required for Ground Truth. During the image analysis process, however, division of the rays into two or more rays occurred. This caused some errors in the measurement of the ray height. To improve the image processing algorithms, further work on combining the fragments of a ray into one ray segment, and increasing the precision of the boundary between rays and the neighboring tissues is required.

Keywords

Acknowledgement

Yoo, H.Y. and Seo, J.W. were supported by the project of 'Collecting Wood Samples and Establishing the Image Database of their Surfaces and Kwon, O. was supported by the project of 'Establishment of Standard Database for Wood Identification and Development of Automatic Identification of Wood Species', which were funded by Korea Forest Service.

References

  1. Alves, E.S., Angyalossy-Alfonso, V. 2000. Ecological trends in the wood anatomy of some Brazilian species. 1. Growth rings and vessels. IAWA Journal 21(1): 3-30. https://doi.org/10.1163/22941932-90000233
  2. Burgert, I., Eckstein, D. 2001. The tensile strength of isolated wood rays of beech (Fagus sylvatica L.) and its significance for the biomechanics of living trees. Trees 15(3): 168-170. https://doi.org/10.1007/s004680000086
  3. Choi, J., Park, J., Kim, S. 2022. Investigation of wood species and conservation status of wooden seated Amitabha Buddha Triad and wooden Amitabha Buddha Altarpiece of Yongmunsa temple, Yecheon, Korea (treasure). Journal of the Korean Wood Science and Technology 50(3): 193-217. https://doi.org/10.5658/WOOD.2022.50.3.193
  4. de Geus, A.R., Backes, A.R., Gontijo, A.B., Albuquerque, G.H.Q., Souza, J.R. 2021. Amazon wood species classification: A comparison between deep learning and pre-designed features. Wood Science and Technology 55(3): 857-872. https://doi.org/10.1007/s00226-021-01282-w
  5. de Palacios, P., Esteban, L.G., Gasson, P., GarciaFernandez, F., de Marco, A., Garcia-Iruela, A., Garcia-Esteban, L., Gonzalez-de-Vega, D. 2020. Using lenses attached to a smartphone as a macroscopic early warning tool in the illegal timber trade, in particular for CITES-listed species. Forests 11(11): 1147.
  6. da Silva, D.B., de Vasconcellos, T.J., Callado, C.H. 2021. Effects of urbanization on the wood anatomy of Guarea guidonia, an evergreen species of the Atlantic forest. Trees. https://doi.org/10.1007/s00468-020-02080-w
  7. Eom, Y.J., Park, B.D. 2018. Wood species identification of documentary woodblocks of Songok clan of the Milseong park, Gyeongju, Korea. Journal of the Korean Wood Science and Technology 46(3): 270-277. https://doi.org/10.5658/WOOD.2018.46.3.270
  8. Fabijanska, A., Danek, M., Barniak, J. 2021. Wood species automatic identification from wood core images with a residual convolutional neural network. Computers and Electronics in Agriculture 181: 105941.
  9. Fathurahman, T., Gunawan, P.H., Prakasa, E., Sugiyama, J. 2021. Wood classification of Japanese Fagaceae using partial sample area and convolutional neural networks. Journal of the Korean Wood Science and Technology 49(5): 491-503. https://doi.org/10.5658/WOOD.2021.49.5.491
  10. Gebregeorgis, E.G., Boniecka, J., Pia̧tkowski, M., Robertson, I., Rathgeber, C.B.K. 2021. SabaTracheid 1.0: A novel program for quantitative analysis of conifer wood anatomy: A demonstration on African juniper from the Blue Nile basin. Frontiers in Plant Science 12: 595258.
  11. GitHub. 2022. Mask R-CNN for object detection and segmentation. https://github.com/matterport/Mask_RCNN
  12. He, K., Gkioxari, G., Dollar, P., Girshick, R. 2017. Mask R-CNN. In: Venice, Italy, Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980-2988.
  13. Hwang, S.W., Tazuru, S., Sugiyama, J. 2020. Wood identification of historical architecture in Korea by synchrotron X-ray microtomography-based three-dimensional microstructural imaging. Journal of the Korean Wood Science and Technology 48(3): 283- 290. https://doi.org/10.5658/WOOD.2020.48.3.283
  14. IAWA Committee. 1989. IAWA list of microscopic features for hardwood identification. IAWA Bulletin 10(3): 219-332. https://doi.org/10.1163/22941932-90000496
  15. IAWA Committee. 2004. IAWA list of microscopic features for softwood identification. IAWA Journal 25(1): 1-70. https://doi.org/10.1163/22941932-90000349
  16. Kim, M.J., Seo, J.W., Kim, B.R. 2018. Anatomical characteristics of Korean red pines according to provinces. Journal of the Korean Wood Science and Technology 46(1): 100-106. https://doi.org/10.5658/WOOD.2018.46.1.100
  17. Kwon, O., Lee, H.G., Lee, M.R., Jang, S., Yang, S.Y., Park, S.Y., Choi, I.G., Yeo, H. 2017. Automatic wood species identification of Korean softwood based on convolutional neural networks. Journal of the Korean Wood Science and Technology 45(6): 797-808. https://doi.org/10.5658/WOOD.2017.45.6.797
  18. Kwon, O., Kim, N.H., Kim, J.S., Seo, J.W., Jeong, Y.J. 2020. Wood Anatomy. The Wood Society of Korea, Seoul, Korea.
  19. Lee, H.M., Bae, J.S. 2021. Major species and anatomical characteristics of the wood used for national use specified in Yeonggeon-Uigwes of the late Joseon dynasty period. Journal of the Korean Wood Science and Technology 49(5): 462-470. https://doi.org/10.5658/WOOD.2021.49.5.462
  20. Lee, H.M., Jeon, W.S., Lee, J.W. 2021b. Analysis of anatomical characteristics for wood species identification of commercial plywood in Korea. Journal of the Korean Wood Science and Technology 49(6): 574-590. https://doi.org/10.5658/WOOD.2021.49.6.574
  21. Lee, K.H., Park, C.H., Kim, S.C. 2021a. Species identification and tree-ring dating of the wooden elements used in Juheulgwan of Joryeong (Gate No.1), Mun- gyeong, Korea. Journal of the Korean Wood Science and Technology 49(6): 550-565. https://doi.org/10.5658/WOOD.2021.49.6.550
  22. Lee, M., Jeong, S.H., Mun, S.P. 2020. Conditions for the extraction of polyphenols from radiata pine (Pinus radiata) bark for bio-foam preparation. Journal of the Korean Wood Science and Technology 48(6): 861-868. https://doi.org/10.5658/WOOD.2020.48.6.861
  23. Lee, S.H., Kwon, S.M., Lee, S.J., Lee, U., Kim, M.J., Kim, N.H. 2009. Radial variation of anatomical characteristics of chestnut wood (Castanea crenata) grown in Korea: Vessel element and ray. Journal of the Korean Wood Science and Technology 37(1): 19-28.
  24. Lopes, D.J.V., Bobadilha, G.S., Burgreen, G.W., Entsminger, E.D. 2021. Identification of North American softwoods via machine-learning. Canadian Journal of Forest Research 51(9): 1245-1252.
  25. Nam, T.G., Kim, H.S. 2021. A fundamental study of the Silla shield through the analysis of the shape, dating, and species identification of wooden shields excavated from the ruins of Wolseong moat in Gyeongju. Journal of the Korean Wood Science and Technology 49(2): 154-168. https://doi.org/10.5658/WOOD.2021.49.2.154
  26. Paredes-Villanueva, K., Espinoza, E., Ottenburghs, J., Sterken, M.G. 2018. Chemical differentiation of Bolivian Cedrela species as a tool to trace illegal timber trade. Forestry: An International Journal of Forest Research 91(5): 539.
  27. Park, S.J., Lee, W.Y., Lee, W.H. 1987. Timber Organization and Identification. Hyangmunsa, Seoul, Korea.
  28. Ravindran, P., Owens, F.C., Wade, A.C., Vega, P., Montenegro, R., Shmulsky, R., Wiedenhoeft, A.C. 2021. Field-deployable computer vision wood identification of Peruvian timbers. Frontiers in Plant Science 12: 647515.
  29. Savero, A.M., Wahyudi, I., Rahayu, I.S., Yunianti, A.D., Ishiguri, F. 2020. Investigating the anatomical and physical-mechanical properties of the 8-year-old superior teakwood planted in Muna island, Indonesia. Journal of the Korean Wood Science and Technology 48(5): 618-630. https://doi.org/10.5658/WOOD.2020.48.5.618
  30. Seo, J.W., Eom, C.D. 2017. Comparisons of Korean red pine tracheid lengths collected from Anmyeondo and Sokwang-ri. Journal of Korea Technical Association of the Pulp and Paper Industry 49(1): 18-24. https://doi.org/10.7584/JKTAPPI.2017.02.49.1.18
  31. Seo, J.W., Eom, C.D., Park, S.Y. 2014. Study on the variations of inter-annual tracheid length for Korean red pine from Sokwang-ri in Uljin. Journal of the Korean Wood Science and Technology 42(6): 646-652. https://doi.org/10.5658/WOOD.2014.42.6.646
  32. von Arx, G., Crivellaro, A., Prendin, A.L., Cufar, K., Carrer, M. 2016. Quantitative wood anatomy: Practical guidelines. Frontiers in Plant Science 7: 781.
  33. Wu, F., Gazo, R., Haviarova, E., Benes, B. 2021. Wood identification based on longitudinal section images by using deep learning. Wood Science and Technology 55(2): 553-563.
  34. Yu, M., Jiao, L., Guo, J., Wiedenhoeft, A.C., He, T., Jiang, X., Yin, Y. 2017. DNA barcoding of vouchered xylarium wood specimens of nine endangered Dalbergia species. Planta 246(6): 1165-1176. https://doi.org/10.1007/s00425-017-2758-9