Morphset:Augmenting categorical emotion datasets with dimensional affect labels using face morphing

TL;DR

This paper introduces Morphset, a face morphing technique that generates synthetic images with dimensional affect labels from categorical emotion datasets, significantly enhancing data augmentation for emotion recognition.

Contribution

The method provides a novel way to augment categorical emotion datasets with dimensional affect labels using face morphing, enabling large-scale data generation.

Findings

Achieves augmentation factors of 20x or more.

Enables controlled distribution of synthetic affective data.

Facilitates dimensional emotion annotation in datasets.

Abstract

Emotion recognition and understanding is a vital component in human-machine interaction. Dimensional models of affect such as those using valence and arousal have advantages over traditional categorical ones due to the complexity of emotional states in humans. However, dimensional emotion annotations are difficult and expensive to collect, therefore they are not as prevalent in the affective computing community. To address these issues, we propose a method to generate synthetic images from existing categorical emotion datasets using face morphing as well as dimensional labels in the circumplex space with full control over the resulting sample distribution, while achieving augmentation factors of at least 20x or more.