Baseline CNN structure analysis for facial expression recognition

TL;DR

This paper evaluates different CNN architectures and image preprocessing techniques to identify the most effective combination for facial expression recognition, demonstrating that a simple three-layer CNN with histogram equalization yields optimal performance.

Contribution

It introduces a systematic analysis of CNN structures and preprocessing methods, identifying the most efficient configuration for facial expression recognition.

Findings

Three-layer CNN with histogram equalization performs best.

Preprocessing methods significantly affect recognition accuracy.

Simple CNN structures can outperform more complex models.

Abstract

We present a baseline convolutional neural network (CNN) structure and image preprocessing methodology to improve facial expression recognition algorithm using CNN. To analyze the most efficient network structure, we investigated four network structures that are known to show good performance in facial expression recognition. Moreover, we also investigated the effect of input image preprocessing methods. Five types of data input (raw, histogram equalization, isotropic smoothing, diffusion-based normalization, difference of Gaussian) were tested, and the accuracy was compared. We trained 20 different CNN models (4 networks x 5 data input types) and verified the performance of each network with test images from five different databases. The experiment result showed that a three-layer structure consisting of a simple convolutional and a max pooling layer with histogram equalization image input was the most efficient. We describe the detailed training procedure and analyze the result of the test accuracy based on considerable observation.