PyLithics: A Python package for stone tool analysis
Jason J. Gellis, Camila Rangel Smith, Robert Foley · The Journal of Open Source Software · 2022
Archaeologists have long used stone tools (lithics) to reconstruct the behaviour of prehistoric hominins.While techniques have become more quantitative, there still remain barriers to optimizing data retrieval (Andrefsky,William, 2012).Machine learning and computer vision approaches can be developed to extract quantitative and trait data from lithics, photographs and drawings.PyLithics has been developed to capture data from 2D line drawings, focusing on the size, shape and technological attributes of flakes.The problems addressed in the software are: one, capturing data in a form that can be quantified, and information maximized; two, solving the challenges of data that is not a simple linear sequence of bases but complex 3D objects or 2D image representations; and three, transforming and exporting these into systematic data for analysis.The goal is to enhance the size and quality of lithic databases for analysing ancient technology and human behaviour.