Multilinear Biased Discriminant Analysis: A Novel Method for Facial Action Unit Representation

TL;DR

This paper introduces a novel multilinear tensor-based discriminant analysis method for facial action unit representation, effectively capturing subtle and temporal facial expression changes, with demonstrated superiority on the Cohn-Kanade database.

Contribution

It proposes the multilinear biased discriminant analysis (MBDA), extending BDA to tensor data, and applies it to facial expression analysis, addressing data asymmetry and high dimensionality.

Findings

MBDA outperforms existing methods on facial expression datasets.

The method effectively captures subtle facial changes and temporal information.

Demonstrates potential for applications in facial recognition and lie detection.

Abstract

In this paper a novel efficient method for representation of facial action units by encoding an image sequence as a fourth-order tensor is presented. The multilinear tensor-based extension of the biased discriminant analysis (BDA) algorithm, called multilinear biased discriminant analysis (MBDA), is first proposed. Then, we apply the MBDA and two-dimensional BDA (2DBDA) algorithms, as the dimensionality reduction techniques, to Gabor representations and the geometric features of the input image sequence respectively. The proposed scheme can deal with the asymmetry between positive and negative samples as well as curse of dimensionality dilemma. Extensive experiments on Cohn-Kanade database show the superiority of the proposed method for representation of the subtle changes and the temporal information involved in formation of the facial expressions. As an accurate tool, this representation can be applied to many areas such as recognition of spontaneous and deliberate facial expressions, multi modal/media human computer interaction and lie detection efforts.