A Data Augmentation Methodology to Improve Age Estimation Using Convolutional Neural Networks

Recent advances in deep learning methodologies are enabling the construction of more accurate classifiers. However, existing labeled face datasets are limited in size, which prevents CNN models from reaching their full generalization capabilities. A variety of techniques to generate new training sam...

Full description

Saved in:
Bibliographic Details
Main Authors: Oliveira, Italo de Pontes, Medeiros, Joao Lucas Peixoto, Sousa, Vinicius Fernandes de, Gomes Teixeira Junior, Adalberto, Torres Pereira, Eanes, Martins Gomes, Herman
Format: Conference Proceeding
Language:English
Subjects:
Active appearance model
Age Estimation
Data Augmentation
Deep Learning
Estimation
Face
Face Detection
Fiducial Points
Machine learning
Neural networks
Shape
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent advances in deep learning methodologies are enabling the construction of more accurate classifiers. However, existing labeled face datasets are limited in size, which prevents CNN models from reaching their full generalization capabilities. A variety of techniques to generate new training samples based on data augmentation have been proposed, but the great majority is limited to very simple transformations. The approach proposed in this paper takes into account intrinsic information about human faces in order to generate an augmented dataset that is used to train a CNN, by creating photo-realistic smooth face variations based on Active Appearance Models optimized for human faces. An experimental evaluation taking CNN models trained with original and augmented versions of the MORPH face dataset allowed an increase of 10% in the F-Score and yielded Receiver Operating Characteristic curves that outperformed state-of-the-art work in the literature.
ISSN:2377-5416
DOI:10.1109/SIBGRAPI.2016.021