Face Recognition from Face Motion Manifolds using Robust Kernel Resistor-Average Distance

Authors:
Ognjen Arandjelovic;Roberto Cipolla
Affiliations:
University of Cambridge, UK;University of Cambridge, UK
Venue:
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 5 - Volume 05
Year:
2004

Citing 0
Cited 7

Toward a theory of information processing

Signal Processing
Identity Management in Face Recognition Systems

Biometrics and Identity Management
Statistical Methods and Models for Video-Based Tracking, Modeling, and Recognition

Foundations and Trends in Signal Processing
Video-based face recognition: state of the art

CCBR'11 Proceedings of the 6th Chinese conference on Biometric recognition
Face recognition using more than one still image: what is more?

SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
Human face analysis: from identity to emotion and intention recognition

ICEB'10 Proceedings of the Third international conference on Ethics and Policy of Biometrics and International Data Sharing
Multi-local model image set matching based on domain description

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work we consider face recognition from face motion manifolds. An information-theoretic approach with Resistor-Average Distance (RAD) as a dissimilarity measure between distributions of face images is proposed. We introduce a kernel-based algorithm that retains the simplicity of the closed-form expression for the RAD between two normal distributions, while allowing for modelling of complex, nonlinear manifolds. Additionally, it is shown how errors in the face registration process can be modelled to significantly improve recognition. Recognition performance of our method is experimentally demonstrated and shown to outperform state-of-the-art algorithms. Recognition rates of 97-100% are consistently achieved on databases of 35-90 people.