Very low resolution face recognition problem

Wilman W.W. Zou*, Pong Chi YUEN

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

443 Citations (Scopus)


This paper addresses the very low resolution (VLR) problem in face recognition in which the resolution of the face image to be recognized is lower than 16 × 16. With the increasing demand of surveillance camera-based applications, the VLR problem happens in many face application systems. Existing face recognition algorithms are not able to give satisfactory performance on the VLR face image. While face super-resolution (SR) methods can be employed to enhance the resolution of the images, the existing learning-based face SR methods do not perform well on such a VLR face image. To overcome this problem, this paper proposes a novel approach to learn the relationship between the high-resolution image space and the VLR image space for face SR. Based on this new approach, two constraints, namely, new data and discriminative constraints, are designed for good visuality and face recognition applications under the VLR problem, respectively. Experimental results show that the proposed SR algorithm based on relationship learning outperforms the existing algorithms in public face databases.

Original languageEnglish
Article number5957296
Pages (from-to)327-340
Number of pages14
JournalIEEE Transactions on Image Processing
Issue number1
Publication statusPublished - Jan 2012

Scopus Subject Areas

  • Software
  • Computer Graphics and Computer-Aided Design

User-Defined Keywords

  • Face recognition
  • face super-resolution (SR)
  • relationship learning
  • very low resolution (VLR)


Dive into the research topics of 'Very low resolution face recognition problem'. Together they form a unique fingerprint.

Cite this