Destek vektör maki̇nesi̇ yöntemi̇ i̇le yüz güzelli̇ǧi̇ karari

H. Irem Türkmen*, Zeyneb Kurt, M. Elif Karsligil

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents an automated facial beauty recognition system based on Support Vector Machine (SVM). First, we constructed manually two classes of female faces with respect to their facial beauty, by requesting personal opinions of people. As the second step, Principal Components Analysis (PCA) is applied to each class for extracting principal components. Then Support Vector Machine (SVM) is used for judging whether a given face is beautiful or not. Judging the beauty of a face is a relative concept so the decision results of our system are compared with the results obtained by asking 50 different people to determine the success of our system. We figured out that the results of our system agreed 85% with the decisions of the people.

Original languageTurkish
Title of host publication2006 IEEE 14th Signal Processing and Communications Applications Conference
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781424402397
DOIs
Publication statusPublished - 17 Apr 2006
Externally publishedYes
Event2006 IEEE 14th Signal Processing and Communications Applications - Antalya, Turkey
Duration: 17 Apr 200619 Apr 2006

Publication series

Name2006 IEEE 14th Signal Processing and Communications Applications Conference
Volume2006

Conference

Conference2006 IEEE 14th Signal Processing and Communications Applications
Country/TerritoryTurkey
CityAntalya
Period17/04/0619/04/06

Cite this