Deep Learning For Smile Recognition

TL;DR

This paper demonstrates the effectiveness of deep convolutional neural networks for smile recognition, achieving near-perfect accuracy and significantly outperforming traditional methods on the DISFA database.

Contribution

It introduces a novel deep learning approach with comprehensive model selection for facial expression recognition, especially smile detection, utilizing GPU acceleration for efficiency.

Findings

Smile recognition accuracy of 99.45% on DISFA database

Outperforms traditional hand-crafted feature methods

GPU-based training accelerates experiments by a factor of 10

Abstract

Inspired by recent successes of deep learning in computer vision, we propose a novel application of deep convolutional neural networks to facial expression recognition, in particular smile recognition. A smile recognition test accuracy of 99.45% is achieved for the Denver Intensity of Spontaneous Facial Action (DISFA) database, significantly outperforming existing approaches based on hand-crafted features with accuracies ranging from 65.55% to 79.67%. The novelty of this approach includes a comprehensive model selection of the architecture parameters, allowing to find an appropriate architecture for each expression such as smile. This is feasible because all experiments were run on a Tesla K40c GPU, allowing a speedup of factor 10 over traditional computations on a CPU.