Dissertation > Excellent graduate degree dissertation topics show

An Adaptive Learning Algorithm for Image Super-resolution

Author: ChenShaoChong
Tutor: ShaoXiaoPeng
School: Xi'an University of Electronic Science and Technology
Course: Optical Engineering
Keywords: adaptive sparse representation super-resolution piecewise autoregressive non-local self-similarity
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 207
Quote: 1
Read: Download Dissertation

Abstract


Super-resolution image reconstruction is a resolution enhancement technology that extracts higher resolution images containing more details from an image sequence of lower resolution by using digital signal processing technology, and the existing low-resolution imaging systems can be still utilized. As a technology of improving image quality significantly without changing the hardware device, super-resolution image reconstruction has a wide range of applications and has become one of the hottest image restoration research topics in the world.As an emerging imaging image modeling technique, sparse representation has been successfully used in various image restoration applications. The image restoration quality largely depends on whether the employed sparse domain can represent effectively the underlying image. In this paper, we present an adaptive learning algorithm for image super-resolution. Its implementation is guaranteed by the combination of adaptive sparse representation super-resolution (ASR_SR) and the adaptive regularization terms. We propose to learn various sets of bases from a pre-collected dataset of high quality example image patches, and then for a given patch to be processed, one or several sets of bases are adaptively selected to characterized the local sparse domain. Furthermore, a set of piecewise autoregressive (PAR) models are learned from the dataset of example image patches. For a given image patch, the best fitted PAR models are selected to regularize the image local structures. Then the image non-local self-similarity (NLSS) is introduced as another regularization term. The two additional regularization models are very helpful in enhancing image edges and suppressing noises, which can further increase the image restoration performance.Extensive experiments on image super-resolution validated that by using adaptive sparse domain selection and the adaptive regularization, the proposed adaptive learning method achieves much better results than the state-of-the-art algorithms in terms of PSNR, SSIM and visual perception.

Related Dissertations

  1. Research on the Super-resolution Technologies of Polarimetric SAR Images,TN957.52
  2. Superresolution of Hyperspectral Images Based on Spatial-Spectral Information Coordination,TN911.73
  3. Research on Learning-Based Super-Resolution and SR System Implementation,TP391.41
  4. Research for Super-resolution Reconstruction Technologies of Image Based on POCS Algorithm,TP391.41
  5. Stepped frequency SAR super-resolution imaging technology,TN957.52
  6. Research on Algorithm of Image Super-resolution Reconstruction,TP391.41
  7. Super Resolution of 3D Surface Texture and Results Evaluation Based on Wavelet Transform,TP391.41
  8. The Research Based on the Restoration Approach of Super-Resolution Distilled from Highway Video Monitoring,TP391.41
  9. Registration method for super-resolution image reconstruction,TP391.41
  10. Research on Restoration Algorithm from Sequence Images for Scene Supervision,TP391.41
  11. License Plate Recognition Super-resolution Algorithm,TP391.41
  12. Research on the Super Resolution Imaging System,TP751
  13. Super-resolution Reconstrction of Image Sequences Based on Interpolation Inverse Projection Iteration,TP391.41
  14. Super-resolution reconstruction algorithm based on the sequence of images of the mixed MAP / POCS,TP391.41
  15. Image super-resolution technique Registration Algorithm,TP391.41
  16. Analysis and Simulation of Super-Resolution Reconstruction from Compressed Video,TP391.41
  17. Super-Resolution Image Reconstruction Based on Image Sequence,TP391.41
  18. Research on Image Super-resolution Reconstruction,TP391.41
  19. Research on Super-resolution Reconstruction from Passive Millimeter Wave Image,TP391.41
  20. Pixel Domain Based Image Super-Resolution Reconstruction Fast Algorithms,TP391.41

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile