Abstract
Recent approaches on single image super-resolution (SR) have attempted to exploit self-similarity to avoid the use of multiple images. In this paper, we propose an SR method based on self-learning and Gabor prior. Given a low resolution (LR) test image I 0 and its coarser resolution version I − 1, both captured from the same camera, we first estimate the degradation between LR and HR (I 1) images by constructing the LR-HR patches from LR test image, I 0. The HR patches are obtained from I 0 by searching for similar patches (of I 0) of the same size in I − 1. A nearest neighbor search is used to find the best LR match which is then used to obtain the parent HR patch from I 0. All such LR-HR patches form self-learned dictionaries. The HR patches that do not find LR match in I − 1 are estimated using self-learned dictionaries constructed from the already found LR-HR patches. A compressive sensing-based method is used to obtain the missing HR patches. The estimated LR-HR pairs are used to obtain the LR image formation model by computing the degradation for each pair. A new prior, called Gabor Prior, based on the outputs of a Gabor filter bank is proposed that restricts the solution space by imposing the condition of preserving the SR features at different frequencies. The experimental results show the effectiveness of the proposed approach.
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
Tian, J., Ma, K.K.: A survey on super-resolution imaging. Signal, Image and Video Processing 5, 329–342 (2011)
Huang, T.S., Tsai, R.Y.: Multi-frame image restoration and registration. Advances in Computer Vision and Image Processing 1, 317–339 (1984)
Irani, M., Peleg, S.: Improving resolution by image registration. CVGIP: Graphical Model and Image Process 53, 231–239 (1991)
Farsiu, S., Robinson, D., Elad, M., Milanfar, P.: Fast and robust multi-frame super-resolution. IEEE Transactions on Image Processing 13, 1327–1344 (2004)
Freeman, W.T., Jones, T.R., Pasztor, E.C.: Example-based super-resolution. IEEE Computer Graphics and Applications 22, 56–65 (2002)
Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. IEEE Transactions on Image Processing 19, 2861–2873 (2010)
Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: ICCV, pp. 349–356 (2009)
Zitová, B., Flusser, J.: Image registration methods: A survey. Image and Vision Computing 21, 977–1000 (2003)
Ur, H., Gross, D.: Improved resolution from subpixel shifted pictures. CVGIP: Graphical Model and Image Process 54, 181–186 (1992)
Baker, S., Kanade, T.: Limits on super-resolution and how to break them. IEEE Trans. Pattern Anal. Mach. Intell. 24, 1167–1183 (2002)
Lin, Z., Shum, H.Y.: Fundamental limits of reconstruction-based superresolution algorithms under local translation. IEEE Transactions on PAMI 26, 83–97 (2004)
Fattal, R.: Image upsampling via imposed edge statistics. ACM Transactions on Graphics 26, 95 (2007)
Sun, J., Xu, Z., Shum, H.Y.: Image super-resolution using gradient profile prior. Computer Vision and Pattern Recognition, 1–8 (2008)
Freedman, G., Fattal, R.: Image and video upscaling from local self-examples. ACM Transactions on Graphics 28, 1–10 (2010)
Gajjar, P., Joshi, M.: New learning based super-resolution: Use of dwt and igmrf prior. IEEE Trans. on Img. Process. 19, 1201–1213 (2010)
Ruderman, D.L., Bialek, W.: Statistics of natural images: Scaling in the woods. Physical Review Letters 73, 814–817 (1994)
Turiel, A., Mato, G., Parga, N., Pierre Nadal, J.: The self-similarity properties of natural images resemble those of turbulent flows. Physical Review Letters 80, 1098–1101 (1998)
Luong, H.Q., Ruzic, T., Pižurica, A., Philips, W.: Single-image super-resolution using sparsity constraints and non-local similarities at multiple resolution scales. In: Proc. SPIE, vol. 7723, pp. 2861–2873 (2010)
Lu, X., Yuan, H., Yuan, Y., Yan, P., Li, L., Li, X.: Local learning-based image super-resolution. In: MMSP, pp. 1–5 (2011)
Donoho, D.L.: Compressed sensing. IEEE Transactions on Information Theory 52, 1289–1306 (2006)
Candes, E.: The restricted isometry property and its implications for compressed sensing. Comptes Rendus Mathematique 346, 589–592 (2008)
Arya, S., Mount, D.M.: Approximate nearest neighbor queries in fixed dimensions. In: SODA, pp. 271–280 (1993)
Petkov, N.: Biologically motivated computationally intensive approaches to image pattern recognition. Future Generation Computer Systems 11, 451–465 (1995)
Hardie, R.C., Barnard, K.J., Armstrong, E.E.: Joint map registration and high-resolution image estimation using a sequence of undersampled images. IEEE Transactions on Image Processing 6, 1621–1633 (1997)
Tian, J., Ma, K.K.: Stochastic super-resolution image reconstruction. Journal of Visual Communication and Image Represention 21, 232–244 (2010)
van Ouwerkerk, J.D.: Image super-resolution survey. Image and Vision Computing 24, 1039–1052 (2006)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing 13, 600–612 (2004)
Zhang, L., Zhang, L., Mou, X., Zhang, D.: Fsim: A feature similarity index for image quality assessment. IEEE Transactions on Image Processing 20, 2378–2386 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Khatri, N., Joshi, M.V. (2013). Image Super-Resolution: Use of Self-learning and Gabor Prior. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds) Computer Vision – ACCV 2012. ACCV 2012. Lecture Notes in Computer Science, vol 7726. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37431-9_32
Download citation
DOI: https://doi.org/10.1007/978-3-642-37431-9_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37430-2
Online ISBN: 978-3-642-37431-9
eBook Packages: Computer ScienceComputer Science (R0)