AI-generated faces show lower morphological diversity then real faces do

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11310%2F24%3A10482233" target="_blank" >RIV/00216208:11310/24:10482233 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=d38Yb7m4lY" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=d38Yb7m4lY</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18778/1898-6773.87.1.06" target="_blank" >10.18778/1898-6773.87.1.06</a>

Jazyk výsledku

angličtina

Název v původním jazyce

AI-generated faces show lower morphological diversity then real faces do

Popis výsledku v původním jazyce

Some recent studies suggest that artificial intelligence can create realistic human faces subjectively unrecognizable from faces of real people. We have compared static facial photographs of 197 real men with a sample of 200 male faces generated by artificial intelligence to test whether they converge in basic morphological characteristic such as shape variation and bilateral asymmetry. Both datasets depicted standardized faces of European men with a neutral expression. Then we used geometric morphometrics to investigate their facial morphology and calculate the measures of shape variation and asymmetry. We found that the natural faces of real individuals were more variable in their facial shape than the artificially generated faces were. Moreover, the artificially synthesized faces showed lower levels of facial asymmetry than the control group. Despite the rapid development of generative adversarial networks, natural faces are thus still statistically distinguishable from the artificial ones by objective measurements. We recommend the researchers in face perception, that aim to use artificially generated faces as ecologically valid stimuli, to check whether their stimuli morphological variance is comparable with that of natural faces in a target population.

Název v anglickém jazyce

AI-generated faces show lower morphological diversity then real faces do

Popis výsledku anglicky

Some recent studies suggest that artificial intelligence can create realistic human faces subjectively unrecognizable from faces of real people. We have compared static facial photographs of 197 real men with a sample of 200 male faces generated by artificial intelligence to test whether they converge in basic morphological characteristic such as shape variation and bilateral asymmetry. Both datasets depicted standardized faces of European men with a neutral expression. Then we used geometric morphometrics to investigate their facial morphology and calculate the measures of shape variation and asymmetry. We found that the natural faces of real individuals were more variable in their facial shape than the artificially generated faces were. Moreover, the artificially synthesized faces showed lower levels of facial asymmetry than the control group. Despite the rapid development of generative adversarial networks, natural faces are thus still statistically distinguishable from the artificial ones by objective measurements. We recommend the researchers in face perception, that aim to use artificially generated faces as ecologically valid stimuli, to check whether their stimuli morphological variance is comparable with that of natural faces in a target population.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10602 - Biology (theoretical, mathematical, thermal, cryobiology, biological rhythm), Evolutionary biology

Projekt

<a href="/cs/project/GA21-10527S" target="_blank" >GA21-10527S: Mezikulturní vzorce v obličejové typikalitě: objasnění provázanosti sextypikality, skupinové typikality a psychologických stereotypů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Anthropological Review

ISSN

1898-6773

e-ISSN

2083-4594

Svazek periodika

87

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

PL - Polská republika

Počet stran výsledku

11

Strana od-do

81-91

Kód UT WoS článku

001613905500006

EID výsledku v databázi Scopus

2-s2.0-85192150927