A Surfeit of Barbarians: Using Facial Recognition Technology to Generate a Dungeons and Dragons Character

As Facial Recognition Technologies (FRTs) are increasingly common in society, it is imperative to support the public in understanding and critiquing their use.We used an existing FRT application to generate characters for Dungeons and Dragons (D&D), a tabletop Role-Playing Game, based solely on an uploaded photograph of a player's face.Results from over 30,000 generated characters demonstrate that an FRT dataset is sufficient to generate simple D&D characters.However, it is essential to interrogate the underlying assumptions that feed into the generated characters and the value that this provides to player groups.This work highlights the biases that are embedded in FRT datasets, particularly in relation to assumptions relating to players' inferred gender.

Authors

Institutions

Publication Details

Published
2025-04-15
DOI
https://doi.org/10.1145/3723498.3723825
Primary Topic
Face recognition and analysis
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A Surfeit of Barbarians: Using Facial Recognition Technology to Generate a Dungeons and Dragons Character

Melissa J. Rogerson, Niels Wouters, Sasha Soraine
Face recognition and analysis
article

A Surfeit of Barbarians: Using Facial Recognition Technology to Generate a Dungeons and Dragons Character

Melissa J. Rogerson, Niels Wouters, Sasha Soraine
article en

Abstract

As Facial Recognition Technologies (FRTs) are increasingly common in society, it is imperative to support the public in understanding and critiquing their use.We used an existing FRT application to generate characters for Dungeons and Dragons (D&D), a tabletop Role-Playing Game, based solely on an uploaded photograph of a player's face.Results from over 30,000 generated characters demonstrate that an FRT dataset is sufficient to generate simple D&D characters.However, it is essential to interrogate the underlying assumptions that feed into the generated characters and the value that this provides to player groups.This work highlights the biases that are embedded in FRT datasets, particularly in relation to assumptions relating to players' inferred gender.

The University of Melbourne (AU)
Australian Research Council
Reduced inequalities
Openalex Percentile: Top 92%
Face recognition and analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.