Skip to main navigation Skip to search Skip to main content

Reconstruction of super-resolution image based on neural network

  • Mei Liu*
  • , Hui Nian Liu
  • , Wei Dong Liu
  • , Yan Zhen Wang
  • , Rong Qing Xu
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • Sci. and Technol. Devmt. Ctr.
  • Beijing Datang Gaohong Network Co.

Research output: Contribution to journalArticlepeer-review

Abstract

The reconstruction of super-resolution image based on backpropagation neural network algorithm is proposed to provide a higher quality reconstructed image with the resolution improved by 4 times to avoid error accumulating of CG iterations and to get high-resolution image by using backpropagation neural network to map the nonlinear processing of reconstruction. It differs from those methods based on equation iterative solution and can greatly improve the quality of super-resolution image.

Original languageEnglish
Pages (from-to)707-710
Number of pages4
JournalHarbin Gongye Daxue Xuebao/Journal of Harbin Institute of Technology
Volume35
Issue number6
StatePublished - Jun 2003

Keywords

  • Conjugate gradient
  • Image reconstruction
  • Neural network
  • Super-resolution

Fingerprint

Dive into the research topics of 'Reconstruction of super-resolution image based on neural network'. Together they form a unique fingerprint.

Cite this