The face-space duality hypothesis: a computational model

TL;DR

This paper introduces a computational model that unifies the representation of invariant identity features and dynamic expression features of faces within a dual-structured face-space, validated through experiments.

Contribution

It proposes the face-space duality hypothesis and develops a mathematical model to unify identity and expression recognition in a single framework.

Findings

Supports both identity and expression recognition

Validates the twofold face-space structure

Demonstrates effectiveness with real facial images

Abstract

Valentine's face-space suggests that faces are represented in a psychological multidimensional space according to their perceived properties. However, the proposed framework was initially designed as an account of invariant facial features only, and explanations for dynamic features representation were neglected. In this paper we propose, develop and evaluate a computational model for a twofold structure of the face-space, able to unify both identity and expression representations in a single implemented model. To capture both invariant and dynamic facial features we introduce the face-space duality hypothesis and subsequently validate it through a mathematical presentation using a general approach to dimensionality reduction. Two experiments with real facial images show that the proposed face-space: (1) supports both identity and expression recognition, and (2) has a twofold structure anticipated by our formal argument.