Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 30988
Single Frame Supercompression of Still Images,Video, High Definition TV and Digital Cinema

Authors: Mario Mastriani


Super-resolution is nowadays used for a high-resolution image produced from several low-resolution noisy frames. In this work, we consider the problem of high-quality interpolation of a single noise-free image. Such images may come from different sources, i.e., they may be frames of videos, individual pictures, etc. On the other hand, in the encoder we apply a downsampling via bidimen-sional interpolation of each frame, and in the decoder we apply a upsampling by which we restore the original size of the image. If the compression ratio is very high, then we use a convolutive mask that restores the edges, eliminating the blur. Finally, both, the encoder and the complete decoder are implemented on General-Purpose computation on Graphics Processing Units (GPGPU) cards. In fact, the mentioned mask is coded inside texture memory of a GPGPU.

Keywords: Image Compression, Super-resolution, Interpolation, General-Purpose computation on Graphics ProcessingUnits

Digital Object Identifier (DOI):

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1681


[1] A. Gilman, D. G. Bailey, S. R. Marsland, "Interpolation Models for Image Super-resolution," in Proc. 4th IEEE International Symposium on Electronic Design, Test & Applications, DELTA 2008, Hong Kong, 2008, pp.55-60.
[2] D. Glassner, S. Bagon, M. Irani. Super-Resolution from a Single Image. Available: e_image_SR.pdf
[3] A. Lukin, A. S. Krylov, A. Nasonov. Image Interpolation by Super- Resolution. Available:
[4] Y. Huang, "Wavelet-based image interpolation using multilayer perceptrons," Neural Comput. & Applic., vol.14, pp.1-10, 2005.
[5] N. Mueller, Y. Lu, and M. N. Do. Image interpolation using multiscale geometric representations. Avalilable:
[6] M. Kraus, M. Eissele, and M. Strengert. GPU-Based Edge-Directed Image Interpolation. Available:
[7] -. NVIDIA CUDA: Best Practices Guide, version 3.0, 2/4/2010. Available: VIDIA_CUDA_BestPracticesGuide.pdf
[8] V. Podlozhnyuk. Image Convolution with CUDA, June 2007. Available: ts/convolutionSeparable/doc/convolutionSeparable.pdf
[9] V. Simek, and R. Rakesh, "GPU Acceleration of 2D-DWT Image Compression in MATLAB with CUDA," in Proc. Second UKSIM European Symposium on Computer Modeling and Simulations, Liverpool, UK, 2008, pp.274-277.
[10] T. C. Wittman, "Variational Approaches to Digital Zooming," Ph.D. dissertation, Dept. Math, Univ. of Minnesota, Saint Paul, MN, 2006.
[11] M. Mastriani, and A. E. Giraldez, "Microarrays denoising via smoothing of coefficients in wavelet domain," International Journal of Biological and Life Sciences, vol. 1:1, pp.7-14, 2005.
[12] M. Mastriani, and A. E. Giraldez, "Enhanced directional smoothing algorithm for edge-preserving smoothing of synthetic-aperture radar images," Journal of Measurement Science Review, vol.4:3, pp.1-11, 2004.
[13] M. Mastriani, and A. E. Giraldez, "Smoothing of coefficients in wavelet domain for speckle reduction in synthetic-aperture radar images," ICGST-GVIP Journal, vol.5:6, pp.1-8, 2005.
[14] M. Mastriani. Directional smoothing for speckle reduction in syntheticaperture radar imagery. Available:
[15] R.C. Gonzalez, R.E. Woods, Digital Image Processing, 2nd Edition, Prentice- Hall, Jan. 2002, pp.675-683.
[16] A.K. Jain, Fundamentals of Digital Image Processing, Englewood Cliffs, New Jersey, 1989.
[17] M. Mastriani, "Denoising and compression in wavelet domain via projection onto approximation coefficients," International Journal of Information and Communication Engineering, vol. 5:1, pp. 20-30, 2009.
[18] C. Kim, K. Choi, K. Hwang, and J. Beom Ra. Learning-based superresolution using a multi-resolution wavelet approach. Available:
[19] C. S. Boon, O. G. Guleryuz, T. Kawahara and, Y. Suzuki, "Sparse superresolution reconstructions of video from mobile devices in digital TV broadcast applications," in Proc. SPIE Conf. on Applications of Digital Image Processing XXIX, in Algorithms, Architectures, and Devices, San Diego, CA, Aug. 2006.
[20] I. E. Richardson, H.264 and MPEG-4 Video Compression: Video Coding for Next Generation Multimedia, Ed. Wiley, N.Y., 2003.
[22] D. E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Ed. Pearson, N.Y., 1989.
[23] .-, Kalman Filtering: Theory and Application, Sorenson H. W. ed., IEEE Press, 1985, New York.
[25] NVIDIA® (NVIDIA Corporation, Santa Clara, CA).
[26] P. S. Mandolesi, P. Julian, A. G. Andreou, "A scalable and programmable simplicial CNN digital pixel processor architecture," IEEE Trans. Circuits and Systems - I: Regular Papers, Vol. 51, No. 5, pp. 988- 996, May 2004.
[27] J. Miano, Compressed Image File Formats: JPEG, PNG, GIF, XBM, BMP; Ed. Addison-Wesley, N.Y., 1999.
[28] T. Acharya, and P-S Tsai, JPEG2000 Standard for Image Compression: Concepts, Algorithms and VLSI Architectures, Ed. Wiley, N.Y., 2005.
[29] MATLAB® R2010b (Mathworks, Natick, MA).