Advanced search
1 file | 1.05 MB Add to list

Lossy image coding in the pixel domain using a sparse steering kernel synthesis approach

Author
Organization
Abstract
Kernel regression has been proven successful for image denoising, deblocking and reconstruction. These techniques lay the foundation for new image coding opportunities. In this paper, we introduce a novel compression scheme: Sparse Steering Kernel Synthesis Coding (SSKSC). This pre- and post-processor for JPEG performs non-uniform sampling based on the smoothness of an image, and reconstructs the missing pixels using adaptive kernel regression. At the same time, the kernel regression reduces the blocking artifacts from the JPEG coding. Crucial to this technique is that non-uniform sampling is performed while maintaining only a small overhead for signalization. Compared to JPEG, SSKSC achieves a compression gain for low bits-per-pixel regions of 50% or more for PSNR and SSIM. A PSNR gain is typically in the 0.0-0.5 bpp range, and an SSIM gain can mostly be achieved in the 0.0-1.0 bpp range.
Keywords
kernel regression, adaptive sampling, compression, sparse steering kernel synthesis, image coding, COMPRESSION STANDARD, RECONSTRUCTION, REGRESSION

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.05 MB

Citation

Please use this url to cite or link to this publication:

MLA
Verhack, Ruben et al. “Lossy Image Coding in the Pixel Domain Using a Sparse Steering Kernel Synthesis Approach.” IEEE International Conference on Image Processing ICIP. New York, NY, USA: IEEE, 2014. 4807–4811. Print.
APA
Verhack, R., Krutz, A., Lambert, P., Van de Walle, R., & Sikora, T. (2014). Lossy image coding in the pixel domain using a sparse steering kernel synthesis approach. IEEE International Conference on Image Processing ICIP (pp. 4807–4811). Presented at the 2014 IEEE International conference on Image Processing (ICIP 2014), New York, NY, USA: IEEE.
Chicago author-date
Verhack, Ruben, Andreas Krutz, Peter Lambert, Rik Van de Walle, and Thomas Sikora. 2014. “Lossy Image Coding in the Pixel Domain Using a Sparse Steering Kernel Synthesis Approach.” In IEEE International Conference on Image Processing ICIP, 4807–4811. New York, NY, USA: IEEE.
Chicago author-date (all authors)
Verhack, Ruben, Andreas Krutz, Peter Lambert, Rik Van de Walle, and Thomas Sikora. 2014. “Lossy Image Coding in the Pixel Domain Using a Sparse Steering Kernel Synthesis Approach.” In IEEE International Conference on Image Processing ICIP, 4807–4811. New York, NY, USA: IEEE.
Vancouver
1.
Verhack R, Krutz A, Lambert P, Van de Walle R, Sikora T. Lossy image coding in the pixel domain using a sparse steering kernel synthesis approach. IEEE International Conference on Image Processing ICIP. New York, NY, USA: IEEE; 2014. p. 4807–11.
IEEE
[1]
R. Verhack, A. Krutz, P. Lambert, R. Van de Walle, and T. Sikora, “Lossy image coding in the pixel domain using a sparse steering kernel synthesis approach,” in IEEE International Conference on Image Processing ICIP, Paris, France, 2014, pp. 4807–4811.
@inproceedings{5973027,
  abstract     = {Kernel regression has been proven successful for image denoising, deblocking and reconstruction. These techniques lay the foundation for new image coding opportunities. In this paper, we introduce a novel compression scheme: Sparse Steering Kernel Synthesis Coding (SSKSC). This pre- and post-processor for JPEG performs non-uniform sampling based on the smoothness of an image, and reconstructs the missing pixels using adaptive kernel regression. At the same time, the kernel regression reduces the blocking artifacts from the JPEG coding. Crucial to this technique is that non-uniform sampling is performed while maintaining only a small overhead for signalization. Compared to JPEG, SSKSC achieves a compression gain for low bits-per-pixel regions of 50% or more for PSNR and SSIM. A PSNR gain is typically in the 0.0-0.5 bpp range, and an SSIM gain can mostly be achieved in the 0.0-1.0 bpp range.},
  author       = {Verhack, Ruben and Krutz, Andreas  and Lambert, Peter and Van de Walle, Rik and Sikora, Thomas },
  booktitle    = {IEEE International Conference on Image Processing ICIP},
  isbn         = {9781479957514},
  issn         = {1522-4880},
  keywords     = {kernel regression,adaptive sampling,compression,sparse steering kernel synthesis,image coding,COMPRESSION STANDARD,RECONSTRUCTION,REGRESSION},
  language     = {eng},
  location     = {Paris, France},
  pages        = {4807--4811},
  publisher    = {IEEE},
  title        = {Lossy image coding in the pixel domain using a sparse steering kernel synthesis approach},
  year         = {2014},
}

Web of Science
Times cited: