<<
Conference/Proceedings | 21th IEEE International Conference on Image Processing |
Start date | 27.10.2014 |
End date | 30.10.2014 |
Address | Paris,France |
Pages | 4807-4811 |
Author(s) | Ruben Verhack, Andreas Krutz , Peter Lambert , Rik Van de Walle, Thomas Sikora |
Title | [Top 10% Paper] LOSSY IMAGE CODING IN THE PIXEL DOMAIN USING A SPARSE STEERING KERNEL SYNTHESIS APPROACH |
Abstract | Kernel regression has been proven successful for image de- noising, deblocking and reconstruction. These techniques lay the foundation for new image coding opportunities. In this pa- per, we introduce a novel compression scheme: Sparse Steer- ing 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 miss- ing 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 over- head 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. |
Key words | compression, image coding; compression; adaptive sampling; kernel regression; sparse steering kernel synthesis |
Note | ISBN: 978-1-4799-5750-7 |
File | 1466Verhack2014.pdf |
BibTeX