Going Deeper in Facial Expression Recognition using Deep Neural Networks

TL;DR

This paper introduces a deep neural network architecture for facial expression recognition that generalizes well across multiple datasets, outperforming traditional methods and existing neural network models in accuracy and training efficiency.

Contribution

The paper presents a novel deep neural network with Inception layers designed specifically for FER, demonstrating improved cross-dataset performance over prior approaches.

Findings

Achieved comparable or superior accuracy to state-of-the-art methods.

Outperformed traditional CNNs in both accuracy and training time.

Proved effective across seven diverse facial expression datasets.

Abstract

Automated Facial Expression Recognition (FER) has remained a challenging and interesting problem. Despite efforts made in developing various methods for FER, existing approaches traditionally lack generalizability when applied to unseen images or those that are captured in wild setting. Most of the existing approaches are based on engineered features (e.g. HOG, LBPH, and Gabor) where the classifier's hyperparameters are tuned to give best recognition accuracies across a single database, or a small collection of similar databases. Nevertheless, the results are not significant when they are applied to novel data. This paper proposes a deep neural network architecture to address the FER problem across multiple well-known standard face datasets. Specifically, our network consists of two convolutional layers each followed by max pooling and then four Inception layers. The network is a single component architecture that takes registered facial images as the input and classifies them into either of the six basic or the neutral expressions. We conducted comprehensive experiments on seven publically available facial expression databases, viz. MultiPIE, MMI, CK+, DISFA, FERA, SFEW, and FER2013. The results of proposed architecture are comparable to or better than the state-of-the-art methods and better than traditional convolutional neural networks and in both accuracy and training time.