Automatic age range estimation on mobile devices

XXV Congresso de Iniciação Científica da Unicamp, Campinas, SP, Brazil, 2017

Abstract

Automatic age estimation research has grown over the last years due to its importance in many applications, such as security control and Biometrics, and many machine-learning techniques have been applied in order to perform the task. This study explores age range estimation using state-of-art techniques based on Convolutional Neural Network and transfer learning (fine tuning). Our experiments show high accuracy for some age ranges in challenging datasets and hint at several improvements to research in the area.

BibTeX

@inproceedings{bertocco17cicunicamp,
    authors      = “Gabriel Bertocco and Fernanda A. Andal{\‘o} and Ricardo da S. Torres and Jacques Wainer and Anderson Rocha”,
    title        = “Automatic age range estimation on mobile devices”,
    booktitle    = “XXV Congresso de Iniciação Científica da Unicamp”,
    year         = 2017,
    address      = “Campinas, SP, Brazil”,
    note         = “short paper”,
}