Skip to Main Content
Classification of CITES-listed and other neotropical Meliaceae wood images using convolutional neural networksAuthor(s): Prabu Ravindran; Adriana Costa; Richard Soares; Alex C. Wiedenhoeft
Source: Plant Methods. 14(1): 790-800.
Publication Series: Scientific Journal (JRNL)
Station: Forest Products Laboratory
Download Publication (1.0 MB)
DescriptionBackground: The current state-of-the-art for feld wood identifcation to combat illegal logging relies on experienced practitioners using hand lenses, specialized identifcation keys, atlases of woods, and feld manuals. Accumulation of this expertise is time-consuming and access to training is relatively rare compared to the international demand for feld wood identifcation. A reliable, consistent and cost efective feld screening method is necessary for efective global scale enforcement of international treaties such as the Convention on the International Trade in Endagered Species (CITES) or national laws (e.g. the US Lacey Act) governing timber trade and imports.
Results: We present highly efective computer vision classifcation models, based on deep convolutional neural networks, trained via transfer learning, to identify the woods of 10 neotropical species in the family Meliaceae, including CITES-listed Swietenia macrophylla, Swietenia mahagoni, Cedrela fssilis, and Cedrela odorata. We build and evaluate models to classify the 10 woods at the species and genus levels, with image-level model accuracy ranging from 87.4 to 97.5%, with the strongest performance by the genus-level model. Misclassifed images are attributed to classes consistent with traditional wood anatomical results, and our species-level accuracy greatly exceeds the resolution of traditional wood identifcation.
Conclusion: The end-to-end trained image classifers that we present discriminate the woods based on digital images of the transverse surface of solid wood blocks, which are surfaces and images that can be prepared and captured in the feld. Hence this work represents a strong proof-of-concept for using computer vision and convolutional neural networks to develop practical models for feld screening timber and wood products to combat illegal logging.
- We recommend that you also print this page and attach it to the printout of the article, to retain the full citation information.
- This article was written and prepared by U.S. Government employees on official time, and is therefore in the public domain.
CitationRavindran, Prabu; Costa, Adriana; Soares, Richard; Wiedenhoeft, Alex C. 2018. Classification of CITES-listed and other neotropical Meliaceae wood images using convolutional neural networks. Plant Methods. 14(1): 790-800.
KeywordsWood identification, illegal logging, CITES, forensic wood anatomy, deep learning, transfer learning, convolutional neural networks
- Image based identification of Ghanaian timbers using the XyloTron: opportunities, risks and challenges
- Machine Learning Models with Quantitative Wood Anatomy Data Can Discriminate between Swietenia macrophylla and Swietenia mahagoni
- Machine learning approaches outperform distance- and tree-based methods for DNA barcoding of Pterocarpus wood
XML: View XML