Super-resolution of text images through neighbor embedding

David Smith

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Single-image super-resolution (SISR) is the problem ofgenerating a high resolution (HR) image from a single low resolution (LR) image, possibly with the help of a set of training images. The SISR technique known as neighbor embedding (NE) is based on the assumption that corresponding small patches in low and high resolution versions of an image form manifolds with similar local geometry. NE utilizes a training ensemble of pairs of low and high resolution image patches, where the patches in a given pair represent the same image region. An input patch from a LR image is approximated by nearby LR training patches and a HR patch estimate is constructed from the corresponding combination of HR training patches. While NE has shown good success for super-resolution of face and scene imagery, little has been reported on NE for enhancing text images. We apply NE to enhance LR text images, and achieve good HR estimates at 2x, 3x and 4x magnification. Our experiments show that NE raises PSNR found with bicubic interpolation (BI) by 68% and 89% at 3x, and 4x magnification, respectively. We show how to naturally extend the original NE luminance features to an arbitrary number, and achieve further improvement in PSNR by adding just one more feature.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Signal and Image Processing, SIP 2011
Pages19-26
Number of pages8
DOIs
StatePublished - 2011
Externally publishedYes
Event13th International Conference on Signal and Image Processing, SIP 2011 - Dallas, TX, United States
Duration: Dec 14 2011Dec 16 2011

Publication series

NameProceedings of the IASTED International Conference on Signal and Image Processing, SIP 2011

Conference

Conference13th International Conference on Signal and Image Processing, SIP 2011
Country/TerritoryUnited States
CityDallas, TX
Period12/14/1112/16/11

Keywords

  • Image enhancement
  • bicubic interpolation
  • neighbor embedding
  • single-image super-resolution

Fingerprint

Dive into the research topics of 'Super-resolution of text images through neighbor embedding'. Together they form a unique fingerprint.

Cite this