Variational shift invariant probabilistic PCA for face recognition

Tu Juin, Aleksandar Ivanovic, Xu Xun, Fei Fei Li, Thomas Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

While PCA learns a subspace that captures the variations of the data, it assumes the collected data is well preprocessed(i.e., the pictures for faces are aligned by eye corners), this usually introduces a huge mount of manual labor for human. While people have been developing automatic eye alignment tools for such purpose, detecting eyes with robustness and accuracy is still an open problem for research. We propose to learn PCA while at the same time eliminating the mis-alignment in the data. We formulate the PCA model in a generative framework, and introduce the mis-alignment as a hidden variable in the model. A novel Variational Message Passing [8] update rules is then derived to learn the parameters. The experiments show that the performance of PCA based face recognition is significantly improved by our algorithm when misalignments exist.

Original languageEnglish (US)
Title of host publicationProceedings - 18th International Conference on Pattern Recognition, ICPR 2006
Pages548-551
Number of pages4
DOIs
StatePublished - Dec 1 2006
Event18th International Conference on Pattern Recognition, ICPR 2006 - Hong Kong, China
Duration: Aug 20 2006Aug 24 2006

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume3
ISSN (Print)1051-4651

Other

Other18th International Conference on Pattern Recognition, ICPR 2006
CountryChina
CityHong Kong
Period8/20/068/24/06

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Variational shift invariant probabilistic PCA for face recognition'. Together they form a unique fingerprint.

Cite this