Face Verification Using Modeled Eigenspectrum

Bappaditya Manda,Alex Kot,Xudong Jiang

doi:10.2174/1874061800802010035

Abstract

Face verification is different from face identification task. Some traditional subspace methods that work well in face identification may suffer from severe over-fitting problem when applied for the verification task. Conventional discriminative methods such as linear discriminant analysis (LDA) and its variants are highly sensitive to the training data, which hinders them from achieving high verification accuracy. This work proposes an eigenspectrum model that alleviates the over-fitting problems by replacing the unreliable small and zero eigenvalues with the model values. It also enables the discriminant evaluation in the whole space to extract the low dimensional features effectively. The proposed approach is evaluated and compared with 8 popular subspace based methods for a face verification task. Experimental results on three face databases show that the proposed method consistently outperforms others.

Highlights

In Biometrics, face recognition has two main applications, one is verification and the other is identification
There are some attempts to distinguish face verification from face identification [4, 5] many works ignore the intrinsic difference between face verification and face identification tasks
There are some intrinsic differences between the face verification and face identification

Summary

Introduction

In Biometrics, face recognition has two main applications, one is verification and the other is identification. Face verification is a task to determine whether a person claiming a given identity is the true claimant or an imposter This can be done by computing the similarity between the probe sample and the samples of the claimed person in the gallery. Over the last decade numerous algorithms using linear as well as nonlinear techniques for face identification have been proposed and considerable good performance has been achieved [1,2,3]. These algorithms focus on face identification and very few of them are evaluated for face verification task. There are some attempts to distinguish face verification from face identification [4, 5] many works ignore the intrinsic difference between face verification and face identification tasks

Methods

Results

Conclusion