Deep Multi-Facial patches Aggregation Network for Expression Classification from Face Images

TL;DR

This paper introduces a deep multi-facial patches aggregation network for face expression recognition, utilizing data augmentation to improve performance on limited datasets, with promising results on CK+ dataset.

Contribution

The paper proposes a novel deep multi-facial patches aggregation framework combined with data augmentation for improved face expression recognition.

Findings

Effective expression classification on CK+ dataset

Data augmentation enhances model performance

Deep features from facial parts improve accuracy

Abstract

Emotional Intelligence in Human-Computer Interaction has attracted increasing attention from researchers in multidisciplinary research fields including psychology, computer vision, neuroscience, artificial intelligence, and related disciplines. Human prone to naturally interact with computers face-to-face. Human Expressions is an important key to better link human and computers. Thus, designing interfaces able to understand human expressions and emotions can improve Human-Computer Interaction (HCI) for better communication. In this paper, we investigate HCI via a deep multi-facial patches aggregation network for Face Expression Recognition (FER). Deep features are extracted from facial parts and aggregated for expression classification. Several problems may affect the performance of the proposed framework like the small size of FER datasets and the high number of parameters to learn. For That, two data augmentation techniques are proposed for facial expression generation to expand the labeled training. The proposed framework is evaluated on the extended Cohn-Konade dataset (CK+) and promising results are achieved.