The current state-of-the-art for field wood identification to combat illegal logging relies on experienced practitioners using hand lenses, specialized identification keys, atlases of woods, and field manuals. Accumulation of this expertise is time-consuming and access to training is relatively rare compared to the international demand for field wood identification. A reliable, consistent and cost effective field screening method is necessary for effective 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. We present highly effective computer vision classification 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 fissilis, 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. Misclassified images are attributed to classes consistent with traditional wood anatomical results, and our species-level accuracy greatly exceeds the resolution of traditional wood identification. The end-to-end trained image classifiers 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 field. Hence this work represents a strong proof-of-concept for using computer vision and convolutional neural networks to develop practical models for field screening timber and wood products to combat illegal logging.

Fraud and misrepresentation in forest products supply chains is often associated with illegal logging, but the extent of fraud in the U.S. forest products market, and the availability of forensic expertise to detect it, is unknown. We used forensic wood anatomy to test 183 specimens from 73 consumer products acquired from major U.S. retailers, surveyed U.S. experts regarding their forensic wood anatomy capacity, and conducted a proficiency-testing program of those experts. 62% of tested products (45 of 73) had one or more type of fraudulent or misrepresented claim. Survey respondents reported a total capacity of 830 wood specimens per year, and participants’ identification accuracy ranged from 6% to 92%. Given the extent of fraud and misrepresentation, U.S. wood forensic wood anatomy capacity does not scale with the need for such expertise. We call for increased training in forensic wood anatomy and its broader application in forest products supply chains to eliminate fraud and combat illegal logging.

Illegal logging and associated trade aggravate the over-exploitation of Swietenia species, of which S. macrophylla King, S. mahagoni (L.) Jacq, and S. humilis Zucc. have been listed in Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES) Appendix Ⅱ. Implementation of CITES necessitates the development of efficient forensic tools to identify wood species accurately, and ideally ones readily deployable in wood anatomy laboratories across the world. Herein, a method using quantitative wood anatomy data in combination with machine learning models to discriminate between three Swietenia species is presented, in addition to a second model focusing only on the two historically more important species S. mahagoni and S. macrophylla. The intra- and inter-specific variations in nine quantitative wood anatomical characters were measured and calculated based on 278 wood specimens, and four machine learning classifiers—Decision Tree C5.0, Naïve Bayes (NB), Support Vector Machine (SVM), and Artificial Neural Network (ANN)—were used to discriminate between the species. Among these species, S. macrophylla exhibited the largest intraspecific variation, and all three species showed at least partly overlapping values for all nine characters. SVM performed the best of all the classifiers, with an overall accuracy of 91.4% and a per-species correct identification rate of 66.7%, 95.0%, and 80.0% for S. humilis, S. macrophylla, and S. mahagoni, respectively. The two-species model discriminated between S. macrophylla and S. mahagoni with accuracies of over 90.0% using SVM. These accuracies are lower than perfect forensic certainty but nonetheless demonstrate that quantitative wood anatomy data in combination with machine learning models can be applied as an efficient tool to discriminate anatomically between similar species in the wood anatomy laboratory. It is probable that a range of previously anatomically inseparable species may become identifiable by incorporating in-depth analysis of quantitative characters and appropriate statistical classifiers.

One rate-limiting factor in the fight against illegal logging is the lack of powerful, affordable, scalable wood identification tools for field screening. Computer vision wood identification using smartphones fitted with customized imaging peripherals offers a potential solution, but to date, such peripherals suffer from one or more weaknesses: low image quality, lack of lighting control, uncontrolled magnification, unknown distortion, and spherical aberration, and/or no access to or publication of the system design. To address cost, optical concerns, and open access to designs and parameters, I present the XyloPhone, a 3D printed research quality macroscopic imaging attachment adaptable to virtually any smartphone. It provides a fixed focal distance, exclusion of ambient light, selection of visible light or UV illumination, uses the lens from a commercially available loupe, is powered by a rechargeable external battery, is fully open-sourced, at a price point of less than USD 110 is a highly affordable tool for the laboratory or the field, and can serve as the foundational hardware for a scalable field-deployable computer vision wood identification system.