Performance evaluation of an automated classifier of female facial beauty

Hatice Gunes, Massimo Piccardi, Tony Jan

Research output: Contribution to conferencePaperpeer-review

Abstract

The fact that facial beauty might be a universal concept and can be measured by using mathematical ratios of facial features has long been debated amongst psychologists and anthropologists. Accordingly, in this paper we present results of experiments to evaluate the extent of universal beauty. The experiments were performed by asking a number of diverse human referees to grade a same collection of female face images. These grades were later compared to the results obtained from an automated classifier. Results obtained prove that the classifier is able to reproduce the human judgment reliably and could be used as an automated tool for objective classification of female facial beauty.

Original languageEnglish
Pages652-656
Number of pages5
Publication statusPublished - 2003
Externally publishedYes
EventProceedings of the International Conference on Imaging Science, Systems and Technology, CISST'03 - Las Vegas, NV, United States
Duration: 23 Jun 200326 Jun 2003

Conference

ConferenceProceedings of the International Conference on Imaging Science, Systems and Technology, CISST'03
Country/TerritoryUnited States
CityLas Vegas, NV
Period23/06/0326/06/03

Keywords

  • Facial beauty classification
  • Facial features
  • Golden proportion
  • Performance evaluation
  • Supervised learning

Fingerprint

Dive into the research topics of 'Performance evaluation of an automated classifier of female facial beauty'. Together they form a unique fingerprint.

Cite this