AMFOrA: Computer Vision for Macroscopic Ceramic Fabric Analysis

Summary

This is an abstract from the "SAA 2024: Individual Abstracts" session, at the 89th annual meeting of the Society for American Archaeology.

The prospect of using computer vision to aid or automate the production of archaeological data is not new to archaeology. Computer vision offers a number of advantages compared to traditional approaches to quantifying archaeological data, including replicability, precision without fatigue, and the ability to expand the size of datasets analyzed. The present research examines the adoption of an automated computer vision protocol for analyzing ceramics from surface surveys. The study of macroscopic elements of ceramic construction, namely the quantification and measurement of temper, non-plastic additions to the raw clay, can produce a wealth of information that allows a nuanced interpretation of archaeological ceramics such as determination of origin or intended vessel use. This type of analysis has distinct potential for survey ceramics where years of surface wear and erosion preclude more common classifications such as form or surface treatment. Since the analysis software takes 2d scans as raw data, data generation is easily integrated into current intensive survey methodologies. This research examines 800 sherds collected over multiple survey seasons throughout the area of Son Servera in Eastern Mallorca (Spain) through an open-source ceramic analysis package developed for Python to generate a deeper understanding of the Son Servera Landscape

This Resource is Part of the Following Collections

• SAA 2024: Individual Abstracts   •
• Society for American Archaeology 89th Annual Meeting, New Orleans, LA (2024)

Keywords

Spatial Coverage

Record Identifiers

Abstract Id(s): 40453.0