Convolutional Neural Networks for Facial Expression Recognition

TL;DR

This paper presents the development and evaluation of convolutional neural networks for facial expression recognition, utilizing raw and hybrid features, GPU acceleration, and visualization techniques to improve accuracy and interpretability.

Contribution

Introduces a novel CNN model combining raw pixel and HOG features, with techniques to reduce overfitting and insights into learned facial features.

Findings

Hybrid CNN with HOG features improves accuracy

GPU acceleration expedites training process

Layer visualizations reveal learned facial features

Abstract

We have developed convolutional neural networks (CNN) for a facial expression recognition task. The goal is to classify each facial image into one of the seven facial emotion categories considered in this study. We trained CNN models with different depth using gray-scale images. We developed our models in Torch and exploited Graphics Processing Unit (GPU) computation in order to expedite the training process. In addition to the networks performing based on raw pixel data, we employed a hybrid feature strategy by which we trained a novel CNN model with the combination of raw pixel data and Histogram of Oriented Gradients (HOG) features. To reduce the overfitting of the models, we utilized different techniques including dropout and batch normalization in addition to L2 regularization. We applied cross validation to determine the optimal hyper-parameters and evaluated the performance of the developed models by looking at their training histories. We also present the visualization of different layers of a network to show what features of a face can be learned by CNN models.