Topological principal component analysis for face encoding and recognition

Albert Pujol, Jordi Vitrià, Felipe Lumbreras, Juan J. Villanueva

    Research output: Contribution to journalArticleResearchpeer-review

    15 Citations (Scopus)

    Abstract

    Principal component analysis (PCA)-like methods make use of an estimation of the covariances between sample variables. This estimation does not take into account their topological relationships. This paper proposes how to use these relationships in order to estimate the covariances in a more robust way. The new method topological principal component analysis (TPCA) is tested using both face encoding and recognition experiments showing how the generalization capabilities of PCA are improved. © 2001 Elsevier Science B.V. All rights reserved.
    Original languageEnglish
    Pages (from-to)769-776
    JournalPattern Recognition Letters
    Volume22
    DOIs
    Publication statusPublished - 1 May 2001

    Keywords

    • Covariance estimation
    • Face recognition
    • Generalization
    • Principal component analysis
    • Topological covariance matrix

    Fingerprint Dive into the research topics of 'Topological principal component analysis for face encoding and recognition'. Together they form a unique fingerprint.

  • Cite this