Abstract
In this paper, we propose a novel learning-based image restoration scheme for compressed images by suppressing compression artifacts and recovering high frequency components with the priors learned from a training set of natural images. Specifically, Deblocking is performed to alleviate the blocking artifacts. Moreover, consistency of the primitives is enhanced by estimating the high frequency components, which are simply truncated during quantization. Furthermore, with the assumption that small image patches in the enhanced and real high frequency images form manifolds with similar local geometry in the corresponding image feature spaces, a neighboring embedding-based mapping strategy is utilized to reconstruct the target high frequency components. And experimental results have demonstrated that the proposed scheme can reproduce higher-quality images in terms of visual quality and PSNR, especially the regions relating to the contours.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Apostolopoulos, J.G., Jayant, N.S.: Postprocessing for Very Low Bit-Rate Video Compression. IEEE Transactions on Image Processing 8(8), 1125–1129 (1999)
Wang, C., Xue, P., Lin, W., Zhang, W., Yu, S.: Fast Edge-Preserved Postprocessing for Compressed Images. IEEE Transactions on Circuits and Systems for Video Technology 16(9), 1142–1147 (2006)
Sheppard, D.G., Bilgin, A., Nadar, M.S., Hunt, B.R., Marcellin, M.W.: A Vector Quantizer for Image Restoration. IEEE Transactions on Image Processing 7(1), 119–124 (1998)
Nakagaki, R., Katsaggelos, A.K.: A VQ-Based Blind Image Restoration Algorithm. IEEE Transaction on Image Processing 12(9), 1044–1053 (2003)
Liaw, Y., Lo, W., Lai, J.Z.: Image Restoration of Compressed Image using Classified Vector Quantization. Pattern Recognition 35, 329–340 (2002)
Freeman, W.T., Pasztor, E., Caemichael, O.: Learning Low-level Vision. International Journal of Computer Vision, 25–47 (2000)
Sun, J., Zheng, N.N., Tao, H., Shum, H.Y.: Image Hallucination with Primitive Sketch Priors. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2003)
Ma, L., Zhang, Y., Lu, Y., Wu, F., Zhao, D.: Three-Tiered Network Model for Image Hallucination. In: International Conference on Image Processing (accepted, 2008)
Roweis, S., Saul, L.: Nonlinear Dimensionality Reduction by Locally Linear Embeddings. Science 290(5500), 2323–2326 (2000)
Marr, D.: Vision: A Computational Investigation into the Human Representation and Processing of Visual Information (1982)
Greenspan, H., Anderson, C.H., Akber, A.: Image Enhancement By Nonlinear Extrapolation in Frequency Space. IEEE Transactions on Image Processing 9(6), 1035–1048 (2000)
Hoen, B.W., Park, R.H., Yang, S.: Resolution Enhancement by Prediction of the High-frequency Image Based on Laplacian Pyramid. EURASIP Journal on Applied Signal Processing 2006, Article ID. 72520 (2006)
Ramponi, G., Polesel, A.: A Rational Unsharp Masking Technique. Journal of Electronic Imaging 7, 333–338 (1998)
Kodak Lossless True color Image Suite, http://r0k.us/graphics/kodak
Pennebaker, W.B., Michell, J.L.: JPEG: Still Image Data Compression Standard. Van Nostrand Reinhold, New York (1993)
Zou, J.J., Yan, H.: A Deblocking Method for BDCT Compressed Images Based on Adaptive Projections. IEEE Transaction on Circuits and Systems for Video Technology 15(3), 430–435 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ma, L., Wu, F., Zhao, D., Gao, W., Ma, S. (2008). Learning-Based Image Restoration for Compressed Image through Neighboring Embedding. In: Huang, YM.R., et al. Advances in Multimedia Information Processing - PCM 2008. PCM 2008. Lecture Notes in Computer Science, vol 5353. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-89796-5_29
Download citation
DOI: https://doi.org/10.1007/978-3-540-89796-5_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-89795-8
Online ISBN: 978-3-540-89796-5
eBook Packages: Computer ScienceComputer Science (R0)