Face Verification in Polar Frequency Domain: a Biologically Motivated Approach

TL;DR

This paper introduces a biologically inspired face verification system that uses Fourier-Bessel Transform on eye regions in the polar frequency domain, demonstrating competitive accuracy and robustness to expression and age variations.

Contribution

The novel approach converts eye regions into the polar frequency domain and embeds them in a dissimilarity space for face verification, outperforming some existing methods.

Findings

Achieved state-of-the-art verification accuracy on FERET database.

System is robust to facial expression and age variations.

Sensitive to registration errors.

Abstract

We present a novel local-based face verification system whose components are analogous to those of biological systems. In the proposed system, after global registration and normalization, three eye regions are converted from the spatial to polar frequency domain by a Fourier-Bessel Transform. The resulting representations are embedded in a dissimilarity space, where each image is represented by its distance to all the other images. In this dissimilarity space a Pseudo-Fisher discriminator is built. ROC and equal error rate verification test results on the FERET database showed that the system performed at least as state-of-the-art methods and better than a system based on polar Fourier features. The local-based system is especially robust to facial expression and age variations, but sensitive to registration errors.