Naslov
Automatic evaluation of facial attractiveness

Autori
Sutić, Davor ; Brešković, Ivan ; Huić, Rene ; Jukić, Ivan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
MIPRO, 2010 Proceedings of the 33rd International Convention Issue Date: 24-28 May 2010 / - Opatija : Hrvatska udruga za informacijsku i komunikacijsku tehnologiju, elektroniku i mikroelektroniku - MIPRO, 2010, 1339-1342

ISBN
978-1-4244-7763-0

Skup
33rd International Convention MIPRO

Mjesto i datum
Opatija, Hrvatska, 24.05.2010. - 28.05.2010

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
machine learning; face representations; neural network; AdaBoost algorithms; facial attractiveness

Sažetak
In this paper we present an approach of applying machine learning algorithms to the task of predicting human attractiveness. We have collected human beauty ratings of female facial images. We have chosen eigenfaces and ratio-based features as face representations. Along with k-nearest neighbors, we have used neural network and AdaBoost algorithms, which had not been used for this task before. Our analysis shows that machine learning algorithms have a preference towards facial symmetry, but also that a wider set of features needs to be included. We validate our results with a survey of four participants, which shows that facial attractiveness is a highly subjective judgement.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA