Robust features for facial action recognition

TL;DR

This paper introduces a new facial gesture recognition system that encodes local motion changes into frequency histograms, demonstrating improved accuracy and robustness across multiple spontaneous face action datasets.

Contribution

The paper proposes a novel encoding method for facial gesture recognition that enhances accuracy and robustness over existing techniques.

Findings

Significant improvement in recognition accuracy

Enhanced robustness across diverse datasets

Effective on spontaneous facial action benchmarks

Abstract

Automatic recognition of facial gestures is becoming increasingly important as real world AI agents become a reality. In this paper, we present an automated system that recognizes facial gestures by capturing local changes and encoding the motion into a histogram of frequencies. We evaluate the proposed method by demonstrating its effectiveness on spontaneous face action benchmarks: the FEEDTUM dataset, the Pain dataset and the HMDB51 dataset. The results show that, compared to known methods, the new encoding methods significantly improve the recognition accuracy and the robustness of analysis for a variety of applications.