Misalignment-robust face recognition

Shuicheng Yan, Huan Wang, Jianzhuang Liu, Xiaoou Tang, Thomas S. Huang

Research output: Contribution to journalArticlepeer-review

Abstract

Subspace learning techniques for face recognition have been widely studied in the past three decades. In this paper, we study the problem of general subspace-based face recognition under the scenarios with spatial misalignments and/or image occlusions. For a given subspace derived from training data in a supervised, unsupervised, or semi-supervised manner, the embedding of a new datum and its underlying spatial misalignment parameters are simultaneously inferred by solving a constrained $\ell-{1}$ norm optimization problem, which minimizes the $\ell-{1}$ error between the misalignment-amended image and the image reconstructed from the given subspace along with its principal complementary subspace. A byproduct of this formulation is the capability to detect the underlying image occlusions. Extensive experiments on spatial misalignment estimation, image occlusion detection, and face recognition with spatial misalignments and/or image occlusions all validate the effectiveness of our proposed general formulation for misalignment-robust face recognition.

Original languageEnglish (US)
Article number5356224
Pages (from-to)1087-1096
Number of pages10
JournalIEEE Transactions on Image Processing
Volume19
Issue number4
DOIs
StatePublished - Apr 2010

Keywords

  • Face recognition
  • Spatial misalignments
  • Subspace learning

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'Misalignment-robust face recognition'. Together they form a unique fingerprint.

Cite this