TY - JOUR
T1 - An information-theoretic approach to face recognition from face motion manifolds
AU - Arandelovic, Oggie
AU - Cipolla, Roberto
PY - 2006/6/1
Y1 - 2006/6/1
N2 - In this work, we consider face recognition from face motion manifolds (FMMs). The use of the resistor-average distance (RAD) as a dissimilarity measure between densities confined to FMMs is motivated in the proposed information-theoretic approach to modelling face appearance. We introduce a kernel-based algorithm that makes use of the simplicity of the closed-form expression for RAD between two Gaussian densities, while allowing for modelling of complex and nonlinear, but intrinsically low-dimensional manifolds. Additionally, it is shown how geodesically local FMM structure can be modelled, naturally leading to a stochastic algorithm for generalizing to unseen modes of data variation. Recognition performance of our method is demonstrated experimentally and is shown to exceed that of state-of-the-art algorithms. Recognition rate of 98% was achieved on a database of 100 people under varying illumination.
AB - In this work, we consider face recognition from face motion manifolds (FMMs). The use of the resistor-average distance (RAD) as a dissimilarity measure between densities confined to FMMs is motivated in the proposed information-theoretic approach to modelling face appearance. We introduce a kernel-based algorithm that makes use of the simplicity of the closed-form expression for RAD between two Gaussian densities, while allowing for modelling of complex and nonlinear, but intrinsically low-dimensional manifolds. Additionally, it is shown how geodesically local FMM structure can be modelled, naturally leading to a stochastic algorithm for generalizing to unseen modes of data variation. Recognition performance of our method is demonstrated experimentally and is shown to exceed that of state-of-the-art algorithms. Recognition rate of 98% was achieved on a database of 100 people under varying illumination.
KW - Face motion manifolds
KW - Face recognition
KW - Kernel
KW - Resistor-average distance
UR - http://www.scopus.com/inward/record.url?scp=33744999621&partnerID=8YFLogxK
U2 - 10.1016/j.imavis.2005.08.002
DO - 10.1016/j.imavis.2005.08.002
M3 - Article
AN - SCOPUS:33744999621
SN - 0262-8856
VL - 24
SP - 639
EP - 647
JO - Image and Vision Computing
JF - Image and Vision Computing
IS - 6
ER -