Resumen
Geometric Morphometrics are a powerful multivariate statistical toolset for the analysis of morphology. While typically used in the study of biological and anatomical variance, modern applications now incorporate these tools into a number of different fields of non-biological origin. Nevertheless, as with many fields of data science, Geometric Morphometric techniques are often impeded by issues concerning sample size. The present study thus evaluates a number of different computational learning algorithms for the augmentation of different datasets. Here we show how generative algorithms from Artificial Intelligence are able to produce highly realistic synthetic data; helping improve the quality of any statistical or predictive modelling applications that may follow.