Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
2 files | 9.61 MB
Add to list
  1. Search results
  2. Advanced wood species identification ...

Advanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion

Kallil M. Zielinski, Leonardo Scabini, Lucas C. Ribas, Núbia R. da Silva, Hans Beeckman, Jan Verwaeren (UGent) , Odemir Martinez Bruno (UGent) and Bernard De Baets (UGent)
(2025) COMPUTERS AND ELECTRONICS IN AGRICULTURE. 231.
Author
Organization
Project
Abstract
Wood is a versatile and renewable resource, widely used across industries, yet the increasing demand has led to illegal logging with severe environmental, social, and economic consequences. To reduce illegal wood trade and its associated threats to biodiversity, robust methods for wood species identification and accurate datasets are crucial. In recent years, there have been significant advances in this area, but many current techniques face challenges such as high costs, the need for skilled experts for data interpretation, and the lack of good datasets for professional reference. Therefore, most of these methods, and certainly the wood anatomical assessment, may benefit from tools based on Artificial Intelligence. In this paper, we apply two transfer learning techniques with Convolutional Neural Networks (CNNs) to a multi-view Congolese wood species dataset including sections from different orientations and viewed at different microscopic magnifications. We explore two feature extraction methods in detail, namely Global Average Pooling (GAP) and Random Encoding of Aggregated Deep Activation Maps (RADAM), for efficient and accurate wood species identification. Our results indicate superior accuracy on diverse datasets and anatomical sections, surpassing the results of other methods. Our proposal represents a significant advancement in wood species identification, offering a robust tool to support the conservation of forest ecosystems and promote sustainable forestry practices.
Keywords
Wood species identification, Texture analysis, Transfer learning, Convolutional neural networks, Feature extraction, NEAR-INFRARED SPECTROSCOPY, TIMBER IDENTIFICATION, SUPPORT, TRADE

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 3.18 MB
  • Download
    AAM COMPAG Advanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 6.43 MB

Citation

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

MLA
Zielinski, Kallil M., et al. “Advanced Wood Species Identification Based on Multiple Anatomical Sections and Using Deep Feature Transfer and Fusion.” COMPUTERS AND ELECTRONICS IN AGRICULTURE, vol. 231, 2025, doi:10.1016/j.compag.2024.109867.
APA
Zielinski, K. M., Scabini, L., Ribas, L. C., da Silva, N. R., Beeckman, H., Verwaeren, J., … De Baets, B. (2025). Advanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 231. https://doi.org/10.1016/j.compag.2024.109867
Chicago author-date
Zielinski, Kallil M., Leonardo Scabini, Lucas C. Ribas, Núbia R. da Silva, Hans Beeckman, Jan Verwaeren, Odemir Martinez Bruno, and Bernard De Baets. 2025. “Advanced Wood Species Identification Based on Multiple Anatomical Sections and Using Deep Feature Transfer and Fusion.” COMPUTERS AND ELECTRONICS IN AGRICULTURE 231. https://doi.org/10.1016/j.compag.2024.109867.
Chicago author-date (all authors)
Zielinski, Kallil M., Leonardo Scabini, Lucas C. Ribas, Núbia R. da Silva, Hans Beeckman, Jan Verwaeren, Odemir Martinez Bruno, and Bernard De Baets. 2025. “Advanced Wood Species Identification Based on Multiple Anatomical Sections and Using Deep Feature Transfer and Fusion.” COMPUTERS AND ELECTRONICS IN AGRICULTURE 231. doi:10.1016/j.compag.2024.109867.
Vancouver
1.
Zielinski KM, Scabini L, Ribas LC, da Silva NR, Beeckman H, Verwaeren J, et al. Advanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion. COMPUTERS AND ELECTRONICS IN AGRICULTURE. 2025;231.
IEEE
[1]
K. M. Zielinski et al., “Advanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion,” COMPUTERS AND ELECTRONICS IN AGRICULTURE, vol. 231, 2025.
@article{01JJBRYY4B0T1W41QVW5PF168X,
  abstract     = {{Wood is a versatile and renewable resource, widely used across industries, yet the increasing demand has led to illegal logging with severe environmental, social, and economic consequences. To reduce illegal wood trade and its associated threats to biodiversity, robust methods for wood species identification and accurate datasets are crucial. In recent years, there have been significant advances in this area, but many current techniques face challenges such as high costs, the need for skilled experts for data interpretation, and the lack of good datasets for professional reference. Therefore, most of these methods, and certainly the wood anatomical assessment, may benefit from tools based on Artificial Intelligence. In this paper, we apply two transfer learning techniques with Convolutional Neural Networks (CNNs) to a multi-view Congolese wood species dataset including sections from different orientations and viewed at different microscopic magnifications. We explore two feature extraction methods in detail, namely Global Average Pooling (GAP) and Random Encoding of Aggregated Deep Activation Maps (RADAM), for efficient and accurate wood species identification. Our results indicate superior accuracy on diverse datasets and anatomical sections, surpassing the results of other methods. Our proposal represents a significant advancement in wood species identification, offering a robust tool to support the conservation of forest ecosystems and promote sustainable forestry practices.}},
  articleno    = {{109867}},
  author       = {{Zielinski, Kallil M. and Scabini, Leonardo and Ribas, Lucas C. and da Silva, Núbia R. and Beeckman, Hans and Verwaeren, Jan and Martinez Bruno, Odemir and De Baets, Bernard}},
  issn         = {{0168-1699}},
  journal      = {{COMPUTERS AND ELECTRONICS IN AGRICULTURE}},
  keywords     = {{Wood species identification,Texture analysis,Transfer learning,Convolutional neural networks,Feature extraction,NEAR-INFRARED SPECTROSCOPY,TIMBER IDENTIFICATION,SUPPORT,TRADE}},
  language     = {{eng}},
  pages        = {{12}},
  title        = {{Advanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion}},
  url          = {{http://doi.org/10.1016/j.compag.2024.109867}},
  volume       = {{231}},
  year         = {{2025}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: