Image Based Identification of Ghanaian Timbers Using the XyloTron: Opportunities, Risks and Challenges

Abstract: Computer vision systems for wood identification have the potential to empower both producer and consumer countries to combat illegal logging if they can be deployed effectively in the field. In this work, carried out as part of an active international partnership with the support of UNIDO, we constructed and curated a field-relevant image data set to train a classifier for wood identification of $15$ commercial Ghanaian woods using the XyloTron system. We tested model performance in the laboratory, and then collected real-world field performance data across multiple sites using multiple XyloTron devices. We present efficacies of the trained model in the laboratory and in the field, discuss practical implications and challenges of deploying machine learning wood identification models, and conclude that field testing is a necessary step - and should be considered the gold-standard - for validating computer vision wood identification systems.