Facial Expression Recognition in Ageing Adults: A Comparative Study

Abstract

Facial Expression Recognition is one of the most active areas of research in computer vision. However, existing approaches lack generalizability and almost all studies ignore the effects of facial attributes, such as age, on expression recognition even though research indicates that facial expression manifestation varies with ages. Recently, a lot of progress has been made in this topic and great improvements in classification task were achieved with the emergence of Deep Learning methods. Such approaches allow to avoid classical hand designed feature extraction methods that generally rely on manual operations with labelled data. In the present work a deep learning approach that utilizes Convolutional Neural Networks (CNNs) to automatically extract features from facial images is evaluated on a benchmark dataset (FACES), the only one present in literature that contains also labelled facial expressions performed by ageing adults. As baselines, with the aim of making a comparison, two traditional machine learning approaches using handcrafted features are evaluated on the same dataset. Our experiments show that the CNN-based approach is very effective in expression recognition performed by ageing adults, significantly improving the baseline approaches, at least with a 8% margin.