A 3D repository of dinosaur teeth: the generation of open resources for the classification and identification of specimens

Abstract

Among the many valuable uses of the artificial intelligence in the field of museums, it may assist the classification of out-of-context items. This paper deals with the problem of the identification of dinosaur teeth (a type of fossil that is usually found scattered), which can be tackled by means of multivariate algorithms (such as the principal components, discriminant or cluster analyses) taking as a starting point a series of morphometric values (i.e., distances between specific points of the fossil tooth). A good interpretation requires some comprehension regarding the mathematical algorithms that are used, as well as the specific knowledge in palaeontology that permits appreciating the actual reach of the results. However, based on metric values as the computations are, there must also be some control over their precision and the possibility of checking the old measurements or complete the list of morphometric variables. This is an aspect that may be solved if the three-dimensional models of the teeth are made publicly available.

The text describes the 3D documentation of a set of twelve fossil teeth of the museum of Natural Sciences of Álava (Vitoria-Gasteiz, Spain) —approximately from 1 to 6 cm in size— using a structured light scanner and close-up photographs for recording some features smaller than the resolution of the scanner. The information about each tooth was then packed and uploaded to the university repository, from where it is also accessible via cultural and scientific aggregators (such as Europeana); likewise, reduced resolution copies are also accessible in the commercial platform Sketchfab®.