Pose invariant virtual classifiers from single training image using novel hybrid-eigenfaces

  • Sharma A
  • Dubey A
  • Tripathi P
 et al. 
  • 6

    Readers

    Mendeley users who have this article in their library.
  • 43

    Citations

    Citations of this article.

Abstract

A novel view-based subspace termed as hybrid-eigenspace is introduced and used to synthesize multiple virtual views of a person under different pose and illumination from a single 2D image. The synthesized virtual views are used as training samples in some subspace classifiers (LDA (Belhumeur et al., 1997) [4], 2D LDA (Kong et al., 2005) [22], 2D CLAFIC (Cevikalp et al., 2009) [23], 2D CLAFIC-γ (Cevikalp et al., 2009) [23], NFL (Pang et al., 2007) [18] and ONFL (Pang et al., 2009) [19]) requiring multiple training image for pose and illumination invariant face recognition. The complete process is termed as virtual classifier and provides efficient solution to the "single sample problem" of aforementioned classifiers. The presented work extends the eigenfaces by introducing hybrid-eigenfaces which are different from the view-based eigenfaces originally proposed by Turk and Pentland (1994) [37]. Hybrid-eigenfaces exhibit properties that are common to faces and eigenfaces. Existence of high correlation between the corresponding hybrid-eigenfaces under different poses (absent in eigenfaces) is one such property. It allows efficient fusion of hybrid-eigenfaces with global linear regression (GLR) (Chai et al., 2007) [36] to synthesize virtual multi-view images which does not require pixel-wise dense correspondence and all the processes are strictly restricted to 2D domain which saves a lot of memory and computation resources. Effectively, PCA and aforementioned subspaces are extended by the presented work and used for more robust face recognition from single training image. Proposed methodology is extensively tested on two databases (FERET and Yale) and the results exhibited significant improvement in terms of tolerance to pose difference and illumination variation between gallery and test images over other 2D methods. © 2010 Elsevier B.V.

Author-supplied keywords

  • Global linear regression
  • Hybrid-GLR
  • Hybrid-eigenfaces
  • Linear discriminant analysis
  • Single training image
  • Virtual multi-view synthesis

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Vinod KumarJaypee University of Information Technology

    Follow
  • Abhishek Sharma

  • Anamika Dubey

  • Pushkar Tripathi

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free