Naslov
A Survey on Neural Networks for Face Age Estimation

Autori
Grd, Petra

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

Izvornik
Proceedings of 32nd Central European Conference on Information and Intelligent Systems / Vrček, Neven ; Pergler, Elisabeth ; Grd, Petra - Varaždin : Fakultet organizacije i informatike Sveučilišta u Zagrebu, 2021, 219-227

Skup
32nd Central European Conference on Information and Intelligent Systems (CECIIS 2021)

Mjesto i datum
Varaždin, Hrvatska, 13.10.2021. - 15.10.2021

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
artificial neural networks ; convolutional neural networks ; age estimation ; age classification ; face ageing

Sažetak
Age estimation is an important task and challenge in computer vision. It can be defined as determining real or apparent age or age group of a person in an image. Through recent years, a large number of age estimation algorithms have been developed and multiple approaches to age estimation have been presented. Nowadays neural networks, especially Convolutional Neural Networks (CNN) have become a standard for age estimation. This paper gives an overview of recent advances in age estimation with focus on neural networks and identifies future research directions. It answers the research questions such as: (RQ1) Which models for age estimation have been used? (RQ2) Which are the most commonly used datasets for testing age estimation algorithms using neural networks? (RQ3) Which performance measures and evaluation protocols are prevalent in age estimation algorithms testing? (RQ4) What is the current state of the art performance for age estimation algorithms using neural networks?

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti

POVEZANOST RADA