The XyloPhone: toward democratizing access to high-quality macroscopic imaging for wood and other substrates

Abstract

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.

Field-Deployable Computer Vision Wood Identification of Peruvian Timbers

“…An easy first step toward rigorous validation is to enforce specimen-level separation between the training and testing splits (as in this work) rather than only image-level separation (most prior works). As affordable mobile phone adaptations (Tang et al, 2018;Wiedenhoeft, 2020) democratize access to these automated technologies, for wider impactful adoption it is critical that they be rigorously evaluated on external validation data. For this work, the next obvious steps will be testing the field model on specimens in Peruvian xylaria; folding in the PACw specimens to train a new field model to test in Peruvian xylaria; folding in the specimens from the Peruvian xylaria to iterate a new field model; and then, taking that model into the real-world and conducting the necessary field-testing coupled with independent forensic validation of the field tested specimens, an approach that should be applied to all modalities (Dormontt et al, 2015) in forensic wood science.…”

“…Recently, the open source XyloTron system , was used to demonstrate a field deployable computer vision wood identification model for fourteen commercial Colombian woods by Arévalo et al (2021). Among these works, it should be noted that XyloTrons have been shown to have comparable/better accuracy than expensive mass spectrometric methods , have been deployed for charcoal identification across the European Union in partnership with the Forest Stewardship Council (as noted in Wiedenhoeft, 2020), and, critically, have been field-tested for wood identification in Ghana (Ravindran et al, 2019). This field testing of a machine learning model on wholly new specimens, ideally by distinct users and using distinct instantiations of the system, especially at the scale undertaken in this work, is lacking in virtually all forensic wood identification literature, regardless of the modality, technique, or the taxa studied.…”

Computer vision-based wood identification and its expansion and contribution potentials in wood science: A review

“…Macroscopic images and stereograms were preferred in studies aimed at developing field-deployable systems because they were easily obtained only by smoothing the wood surface [ 49 , 51 , 57 , 70 ]. Microscopic level features extracted from micrographs allow for an anatomical approach because the image scale is the same as that used in established wood anatomy [ 48 , 73 , 74 ].…”

“…In image capturing, the quality of the obtained images can vary depending on lighting conditions. Imaging modules equipped with optical systems have been used to control the lighting uniformly [21,51,57], and image processing techniques such as filtering were applied to normalize the brightness of the captured images [58][59][60][61]. Digital image processing is to be covered in section preprocessing.…”

“…Early studies generally approached wood identification as a matter of texture classification because cross sections of wood represent different anatomical arrangements, namely different patterns, depending on the species [20,26,82,101,110]. Textures are the image features that were most preferred in published studies, and this is closely related to the finding that stereograms and macroscopic images were preferred for developing fielddeployable systems [21,49,57,69].…”