Banner for LabNotes
From Lab Notes
Contact Information
Forest Products Laboratory
One Gifford Pinchot Drive
Madison, WI 53726-2398
Phone: (608) 231-9200
Fax: (608) 231-9592
Email

 

You are here: FPL Home  / Information Products & Services  / Publications

Requested Product

Title: Classification of CITES-listed and other neotropical Meliaceae wood images using convolutional neural networks

Source: Plant Methods. 14(1): 790-800.

Author(s)Ravindran, Prabu ; Costa, Adriana ; Soares, Richard ; Wiedenhoeft, Alex C.

Publication Year: 2018  View PDF »

Category: Journal Articles
Associated Research Project(s):   FPL-4715-3

Abstract: Background: 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.

Keywords: Wood identification; illegal logging; CITES; forensic wood anatomy; deep learning; transfer learning; convolutional neural networks

Publication Review Process: Formally Refereed

File size: 1,024 kb(s)

Date posted: 03/01/2019

This publication is also viewable on Treesearch:  view
RITS Product ID: 93688
Current FPL Scientist associated with this product
Wiedenhoeft, Alex C.
Research Botanist
  

Additional items that might interest you
View the video celebrating FPL's 100 years of public service in 2010, from the producers of the Greatest Good....view

Research Highlights from FPL....view

Termite Eradication: A search for the Holy Grail.... view

Moisture Management in Residential Construction Series videos...view

Wood Floor Systems in Residential Construction Series videos....view
- FPL's Mission and Strategic Plan -

FPL's mission is to identify and conduct innovative wood and fiber utilization research that contributes to conservation and productivity of the forest resource, thereby sustaining forests, the economy, and quality of life. ... ..more »

- FPL Research Emphasis Areas -
Advanced Composites

As an integral part of the FPL mission, we improve the long-term sustainability of our Nation's forests by creating valuable composite products from biobased materials ... ..more »


Advanced Structures

The FPL has been in the forefront of wood-frame housing research since 1910 and has long been recognized as a world leader in such housing-related areas as engineered wood ... ..more »


Forest Biorefinery

We all know the compelling reasons that the United States needs to reduce its dependence on fossil fuels. Historically, the greatest increases in energy demand have been for transportation fuels ... ..more »


Nanotechnology

A leader in wood products research for over a century, the FPL is positioning itself to become the lead Federal research facility for the application of nanotechnology in forest products ... more »


Woody Biomass Utilization

Forests in the United States contain a substantial amount of small-diameter, overstocked, and underutilized material.FPL research projects are exploring the potential of the small-diameter ... ..more »