Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 5.00 MB
Add to list
  1. Search results
  2. Improved wood species identification ...

Improved wood species identification based on multi-view imagery of the three anatomical planes

Núbia Rosa da Silva, Victor Deklerck, Jan Baetens (UGent) , Jan Van den Bulcke (UGent) , Maaike De Ridder, Melissa Rousseau, Odemir Martinez Bruno, Hans Beeckman, Joris Van Acker (UGent) , Bernard De Baets (UGent) , et al.
(2022) PLANT METHODS. 18(1).
Author
Organization
Project
Abstract
Background The identification of tropical African wood species based on microscopic imagery is a challenging problem due to the heterogeneous nature of the composition of wood combined with the vast number of candidate species. Image classification methods that rely on machine learning can facilitate this identification, provided that sufficient training material is available. Despite the fact that the three main anatomical sections contain information that is relevant for species identification, current methods only rely on transverse sections. Additionally, commonly used procedures for evaluating the performance of these methods neglect the fact that multiple images often originate from the same tree, leading to an overly optimistic estimate of the performance. Results We introduce a new image dataset containing microscopic images of the three main anatomical sections of 77 Congolese wood species. A dedicated multi-view image classification method is developed and obtains an accuracy (computed using the naive but common approach) of 95%, outperforming the single-view methods by a large margin. An in-depth analysis shows that naive accuracy estimates can lead to a dramatic over-prediction, of up to 60%, of the accuracy. Conclusions Additional images from non-transverse sections can boost the performance of machine-learning-based wood species identification methods. Additionally, care should be taken when evaluating the performance of machine-learning-based wood species identification methods to avoid an overestimation of the performance.
Keywords
NEAR-INFRARED SPECTROSCOPY, TIMBER IDENTIFICATION, CLASSIFICATION, TRADE, Wood species identification, Wood anatomical sections, Texture analysis, Machine vision, Machine learning

Downloads

  • Download
    published.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 5.00 MB

Citation

Please use this url to cite or link to this publication:

MLA
Rosa da Silva, Núbia, et al. “Improved Wood Species Identification Based on Multi-View Imagery of the Three Anatomical Planes.” PLANT METHODS, vol. 18, no. 1, 2022, doi:10.1186/s13007-022-00910-1.
APA
Rosa da Silva, N., Deklerck, V., Baetens, J., Van den Bulcke, J., De Ridder, M., Rousseau, M., … Verwaeren, J. (2022). Improved wood species identification based on multi-view imagery of the three anatomical planes. PLANT METHODS, 18(1). https://doi.org/10.1186/s13007-022-00910-1
Chicago author-date
Rosa da Silva, Núbia, Victor Deklerck, Jan Baetens, Jan Van den Bulcke, Maaike De Ridder, Melissa Rousseau, Odemir Martinez Bruno, et al. 2022. “Improved Wood Species Identification Based on Multi-View Imagery of the Three Anatomical Planes.” PLANT METHODS 18 (1). https://doi.org/10.1186/s13007-022-00910-1.
Chicago author-date (all authors)
Rosa da Silva, Núbia, Victor Deklerck, Jan Baetens, Jan Van den Bulcke, Maaike De Ridder, Melissa Rousseau, Odemir Martinez Bruno, Hans Beeckman, Joris Van Acker, Bernard De Baets, and Jan Verwaeren. 2022. “Improved Wood Species Identification Based on Multi-View Imagery of the Three Anatomical Planes.” PLANT METHODS 18 (1). doi:10.1186/s13007-022-00910-1.
Vancouver
1.
Rosa da Silva N, Deklerck V, Baetens J, Van den Bulcke J, De Ridder M, Rousseau M, et al. Improved wood species identification based on multi-view imagery of the three anatomical planes. PLANT METHODS. 2022;18(1).
IEEE
[1]
N. Rosa da Silva et al., “Improved wood species identification based on multi-view imagery of the three anatomical planes,” PLANT METHODS, vol. 18, no. 1, 2022.
@article{8759909,
  abstract     = {{Background The identification of tropical African wood species based on microscopic imagery is a challenging problem due to the heterogeneous nature of the composition of wood combined with the vast number of candidate species. Image classification methods that rely on machine learning can facilitate this identification, provided that sufficient training material is available. Despite the fact that the three main anatomical sections contain information that is relevant for species identification, current methods only rely on transverse sections. Additionally, commonly used procedures for evaluating the performance of these methods neglect the fact that multiple images often originate from the same tree, leading to an overly optimistic estimate of the performance. Results We introduce a new image dataset containing microscopic images of the three main anatomical sections of 77 Congolese wood species. A dedicated multi-view image classification method is developed and obtains an accuracy (computed using the naive but common approach) of 95%, outperforming the single-view methods by a large margin. An in-depth analysis shows that naive accuracy estimates can lead to a dramatic over-prediction, of up to 60%, of the accuracy. Conclusions Additional images from non-transverse sections can boost the performance of machine-learning-based wood species identification methods. Additionally, care should be taken when evaluating the performance of machine-learning-based wood species identification methods to avoid an overestimation of the performance.}},
  articleno    = {{79}},
  author       = {{Rosa da Silva, Núbia and Deklerck, Victor and Baetens, Jan and Van den Bulcke, Jan and De Ridder, Maaike and Rousseau, Melissa and Bruno, Odemir Martinez and Beeckman, Hans and Van Acker, Joris and De Baets, Bernard and Verwaeren, Jan}},
  issn         = {{1746-4811}},
  journal      = {{PLANT METHODS}},
  keywords     = {{NEAR-INFRARED SPECTROSCOPY,TIMBER IDENTIFICATION,CLASSIFICATION,TRADE,Wood species identification,Wood anatomical sections,Texture analysis,Machine vision,Machine learning}},
  language     = {{eng}},
  number       = {{1}},
  pages        = {{17}},
  title        = {{Improved wood species identification based on multi-view imagery of the three anatomical planes}},
  url          = {{http://doi.org/10.1186/s13007-022-00910-1}},
  volume       = {{18}},
  year         = {{2022}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: