A novel face-hallucination scheme based on singular value decomposition

Muwei Jian, Kin Man Lam, Junyu Dong

Research output: Journal article publicationJournal articleAcademic researchpeer-review

45 Citations (Scopus)

Abstract

In this paper, an efficient mapping model based on singular value decomposition (SVD) is proposed for face hallucination. We can observe and prove that the main singular values of an image at one resolution have approximately linear relationships with their counterparts at other resolutions. This makes the estimation of the singular values of the corresponding high-resolution (HR) face images from a low-resolution (LR) face image more reliable. From the signal-processing point of view, this can effectively preserve and reconstruct the dominant information in the HR face images. Interpolating the other two matrices obtained from the SVD of the LR image does not change either the primary facial structure or the pattern of the face image. The corresponding two matrices for the HR face images can be constructed in a "coarse-to- fine" manner using global reconstruction. Our proposed method retains the holistic structure of face images, while the learned mapping matrices, which are represented as embedding coefficients of the individual mapping matrices learned from LR-HR training pairs, can be seen as holistic constraints in the reconstruction of HR images. Compared to state-of-the-art algorithms, experiments show that our proposed face-hallucination scheme is effective in terms of producing plausible HR images with both a holistic structure and high-frequency details.
Original languageEnglish
Pages (from-to)3091-3102
Number of pages12
JournalPattern Recognition
Volume46
Issue number11
DOIs
Publication statusPublished - 1 Nov 2013

Keywords

  • Face hallucination
  • Face super-resolution
  • Holistic constraints
  • Mapping model
  • Singular value decomposition

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this