Computer-assisted timber identification based on features extracted from microscopic wood sections

IAWA Journal - KU Leuven/IAWA Journal, vol. 41, pp. 660–680

Abstract

Abstract Wood anatomy is one of the most important methods for timber identification. However, training wood anatomy experts is time-consuming, while at the same time the number of senior wood anatomists with broad taxonomic expertise is declining. Therefore, we want to explore how a more automated, computer-assisted approach can support accurate wood identification based on microscopic wood anatomy. For our exploratory research, we used an available image dataset that has been applied in several computer vision studies, consisting of 112 — mainly neotropical — tree species representing 20 images of transverse sections for each species. Our study aims to review existing computer vision methods and compare the success of species identification based on (1) several image classifiers based on manually adjusted texture features, and (2) a state-of-the-art approach for image classification based on deep learning, more specifically Convolutional Neural Networks (CNNs). In support of previous studies, a considerable increase of the correct identification is accomplished using deep learning, leading to an accuracy rate up to 95.6%. This remarkably high success rate highlights the fundamental potential of wood anatomy in species identification and motivates us to expand the existing database to an extensive, worldwide reference database with transverse and tangential microscopic images from the most traded timber species and their look-a-likes. This global reference database could serve as a valuable future tool for stakeholders involved in combatting illegal logging and would boost the societal value of wood anatomy along with its collections and experts.

Authors 8

1. Frederic Lens corresponding Aachen Naturalis Biodiversity Center 1Naturalis Biodiversity Center

   Leiden University · Naturalis Biodiversity Center

   Affiliation as printed

   Naturalis Biodiversity Center, Leiden University, P.O. Box 9517, 2300 RA Leiden, The Netherlands

   1Naturalis Biodiversity Center, Leiden University, P.O. Box 9517, 2300 RA Leiden, The Netherlands

2. Chao Liang Aachen Section Imaging and BioInformatics Leiden Institute of Advanced Computer Science 2Section Imaging and BioInformatics

   Leiden University

   Affiliation as printed

   Section Imaging and BioInformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, The Netherlands

   2Section Imaging and BioInformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, The Netherlands

3. Yuanhao Guo Aachen Section Imaging and BioInformatics Leiden Institute of Advanced Computer Science 2Section Imaging and BioInformatics

   Leiden University

   Affiliation as printed

   Section Imaging and BioInformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, The Netherlands

   2Section Imaging and BioInformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, The Netherlands

4. Xiaoqin Tang Aachen Section Imaging and BioInformatics Leiden Institute of Advanced Computer Science 2Section Imaging and BioInformatics

   Leiden University

   Affiliation as printed

   Section Imaging and BioInformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, The Netherlands

   2Section Imaging and BioInformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, The Netherlands

5. Mehrdad Jahanbanifard Aachen Naturalis Biodiversity Center Section Imaging and BioInformatics Leiden Institute of Advanced Computer Science 1Naturalis Biodiversity Center 2Section Imaging and BioInformatics

   Leiden University · Naturalis Biodiversity Center

   Affiliation as printed

   Naturalis Biodiversity Center, Leiden University, P.O. Box 9517, 2300 RA Leiden, The Netherlands

   Section Imaging and BioInformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, The Netherlands

   1Naturalis Biodiversity Center, Leiden University, P.O. Box 9517, 2300 RA Leiden, The Netherlands

   2Section Imaging and BioInformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, The Netherlands

6. Flávio Soares Corrêa da Silva

   Universidade de São Paulo

   Affiliation as printed

   Instituto de Matemática e Estatística, Universidade de São Paulo, São Paulo, SP, Brazil

   3Instituto de Matemática e Estatística, Universidade de São Paulo, São Paulo, SP, Brazil

7. Gregório Ceccantini

   Universidade de São Paulo

   Affiliation as printed

   Laboratório de Anatomia Vegetal, Departamento de Botânica, Instituto de Biociências, Universidade de São Paulo, São Paulo, SP, Brazil

   4Laboratório de Anatomia Vegetal, Departamento de Botânica, Instituto de Biociências, Universidade de São Paulo, São Paulo, SP, Brazil

8. Fons J. Verbeek Aachen Section Imaging and BioInformatics Leiden Institute of Advanced Computer Science 2Section Imaging and BioInformatics

   Leiden University

   Affiliation as printed

   Section Imaging and BioInformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, The Netherlands

   2Section Imaging and BioInformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Leiden, The Netherlands