Super-resolution reconstruction based on linear interpolation of wavelet coefficients

Chong Sze TONG, K. T. Leung*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

14 Citations (Scopus)

Abstract

High resolution image reconstruction is an image process to reconstruct a high resolution image from a set of blurred, degraded and shifted low resolution images. In this paper, the reconstruction problem is treated as a function approximation. We use linear interpolation to build up an algorithm to obtain the relationship between the detail coefficients in wavelet subbands and the set of low resolution images. We use Haar wavelet as an example and establish the connection between the Haar wavelet subband and the low resolution images. Experiments show that we can use just 3 low resolution images to obtain a high resolution image which has better quality than Tikhonov least-squares approach and Chan et al. Algorithm 3 in low noise cases. We also propose an error correction extension for our method which can lead to very good results even in noisy cases. Moreover, our approach is very simple to implement and very efficient.

Original languageEnglish
Pages (from-to)153-171
Number of pages19
JournalMultidimensional Systems and Signal Processing
Volume18
Issue number2-3
DOIs
Publication statusPublished - Sep 2007

Scopus Subject Areas

  • Software
  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Artificial Intelligence
  • Applied Mathematics

User-Defined Keywords

  • Haar Wavelet
  • High resolution image reconstruction
  • Local Wiener filtering
  • NormalShrink

Fingerprint

Dive into the research topics of 'Super-resolution reconstruction based on linear interpolation of wavelet coefficients'. Together they form a unique fingerprint.

Cite this