Imaged based identification of colombian timbers using the xylotron: a proof of concept international partnership

Abstract

Field deployable computer vision wood identification systems can play a key role in combating illegal logging in the real world. This work used 764 xylarium specimens from 84 taxa to develop an image data set to train a classifier to identify 14 commercial Colombian timbers. We imaged specimens from various xylaria outside Colombia, trained and evaluated an initial identification model, then collected additional images from a Colombian xylarium (BOFw), and incorporated those images to refine and produce a final model. The specimen classification accuracy of this final model was ~ 97%, demonstrating that including local specimens can augment the accuracy and reliability of the XyloTron system. Our study demonstrates the first deployable computer vision model for wood identification in Colombia, developed on a timescale of months rather than years by leveraging international cooperation. We conclude that field testing and advanced forensic and machine learning training are the next logical steps.

Keywords

• wood identification
• forensic wood anatomy
• deep learning
• transfer learning
• machine learning