Rapid and brief communication: Intrapersonal subspace analysis with application to adaptive Bayesian face recognition

Authors:
Liwei Wang;Xiao Wang;Jufu Feng
Affiliations:
School of Electronic Engineering & Computer Science, Center for Information Sciences, Peking University, Peking 100871, China;School of Electronic Engineering & Computer Science, Center for Information Sciences, Peking University, Peking 100871, China;School of Electronic Engineering & Computer Science, Center for Information Sciences, Peking University, Peking 100871, China
Venue:
Pattern Recognition
Year:
2005

Citing 2
Cited 3

Lambertian Reflectance and Linear Subspaces

IEEE Transactions on Pattern Analysis and Machine Intelligence
A study on speaker adaptation of the parameters of continuousdensity hidden Markov models

IEEE Transactions on Signal Processing

Rapid and brief communication: Further results on the subspace distance

Pattern Recognition
On subspace distance

ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part II
A real-time system for head tracking and pose estimation

ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part I

Quantified Score

Hi-index	0.01

Visualization

Abstract

We propose a subspace distance measure to analyze the similarity between intrapersonal face subspaces, which characterize the variations between face images of the same individual. We call the conventional intrapersonal subspace the average intrapersonal subspace (AIS) because the image differences often come from a large number of persons. We call an intrapersonal subspace specific intrapersonal subspace (SIS) if the image differences are from just one person. We demonstrate that SIS varies from person to person and most SISs are not similar to AIS. Based on these observations, we introduce the maximum a posteriori (MAP) adaptation to the problem of SIS estimation, and apply it to the Bayesian face recognition algorithm. Experimental results show that the adaptive Bayesian algorithm outperforms the non-adaptive Bayesian algorithm as well as Eigenface and Fisherface methods when a small number of adaptation images are available.