The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.06 - June (2010 vol.32)
pp: 1127-1133
Kwang In Kim , Max-Planck-Institut für biologische Kybernetik Spemannstr, Tübingen
Younghee Kwon , KAIST, Daejeon
ABSTRACT
This paper proposes a framework for single-image super-resolution. The underlying idea is to learn a map from input low-resolution images to target high-resolution images based on example pairs of input and output images. Kernel ridge regression (KRR) is adopted for this purpose. To reduce the time complexity of training and testing for KRR, a sparse solution is found by combining the ideas of kernel matching pursuit and gradient descent. As a regularized solution, KRR leads to a better generalization than simply storing the examples as has been done in existing example-based algorithms and results in much less noisy images. However, this may introduce blurring and ringing artifacts around major edges as sharp changes are penalized severely. A prior model of a generic image class which takes into account the discontinuity property of images is adopted to resolve this problem. Comparison with existing algorithms shows the effectiveness of the proposed method.
INDEX TERMS
Computer vision, machine learning, image enhancement, display algorithms.
CITATION
Kwang In Kim, Younghee Kwon, "Single-Image Super-Resolution Using Sparse Regression and Natural Image Prior", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.32, no. 6, pp. 1127-1133, June 2010, doi:10.1109/TPAMI.2010.25
REFERENCES
[1] M.F. Tappen, B.C. Russel, and W.T. Freeman, "Exploiting the Sparse Derivative Prior for Super-Resolution and Image Demosaicing," Proc. IEEE Workshop Statistical and Computational Theories of Vision, 2003.
[2] D. Tschumperlé and R. Deriche, "Vector-Valued Image Regularization with PDEs: A Common Framework for Different Applications," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 4, pp. 506-517, Apr. 2005.
[3] S. Dai, M. Han, W. Xu, Y. Wu, and Y. Gong, "Soft Edge Smothness Prior for Alpha Channel Super Resolution," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 1-8, 2007.
[4] R. Fattal, "Image Upsampling via Imposed Edge Statistics," ACM Trans. Graphics, vol. 26, no. 3, pp. 95:1-95:8, 2007.
[5] S. Baker and T. Kanade, "Limits on Super-Resolution and How to Break Them," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 9, pp. 1167-1183, Sept. 2002.
[6] W.T. Freeman, E.C. Pasztor, and O.T. Carmichael, "Learning Low-Level Vision," Int'l J. Computer Vision, vol. 40, no. 1, pp. 25-47, 2000.
[7] W.T. Freeman, T.R. Jones, and E.C. Pasztor, "Example-Based Super-Resolution," IEEE Computer Graphics and Applications, vol. 22, no. 2, pp. 56-65, Mar./Apr. 2002.
[8] A. Hertzmann, C.E. Jacobs, N. Oliver, B. Curless, and D.H. Salesin, "Image Analogies," Proc. ACM SIGGRAPH '01, pp. 327-340, 2001.
[9] K.I. Kim, M.O. Franz, and B. Schölkopf, "Iterative Kernel Principal Component Analysis for Image Modeling," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 9, pp. 1351-1366, Sept. 2005.
[10] L.C. Pickup, S.J. Roberts, and A. Zissermann, "A Sampled Texture Prior for Image Super-Resolution," Advances in Neural Information Processing Systems, MIT Press, 2004.
[11] C.V. Jiji and S. Chaudhuri, "Single-Frame Image Super-Resolution through Contourlet Learning," J. Multidimensional System and Signal Processing, vol. 2006, pp. 1-11, 2006.
[12] H. Chang, D.-Y. Yeung, and Y. Xiong, "Super-Resolution through Neighbor Embedding," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 275-282, 2004.
[13] D. Datsenko and M. Elad, "Example-Based Single Image Super-Resolution: A Global MAP Approach with Outlier Rejection," J. Multidimensional System and Signal Processing, vol. 18, nos. 2/3, pp. 103-121, 2007.
[14] T. Hastie, R. Tibshirani, and J.H. Friedman, The Elements of Statistical Learning. Springer-Verlag, 2001.
[15] K.I. Kim, D.H. Kim, and J.-H. Kim, "Example-Based Learning for Image Super-Resolution," Proc. Third Tsinghua-KAIST Joint Workshop Pattern Recognition, pp. 140-148, 2004.
[16] K. Ni and T.Q. Nguyen, "Image Superresolution Using Support Vector Regression," IEEE Trans. Image Processing, vol. 16, no. 6, pp. 1596-1610, June 2007.
[17] K.I. Kim and Y. Kwon, "Example-Based Learning for Single Image Super-Resolution," Proc. DAGM, pp. 456-465, 2008.
[18] P. Vincent and Y. Bengio, "Kernel Matching Pursuit," Machine Learning, vol. 48, pp. 165-187, 2002.
[19] B. Schölkopf and A. Smola, Learning with Kernels. MIT Press, 2002.
[20] E. Snelson and Z. Ghahramani, "Sparse Gaussian Processes Using Pseudo Inputs," Advances in Neural Information Processing Systems, MIT Press, 2006.
[21] S.S. Keerthi and W. Chu, "A Matching Pursuit Approach to Sparse Gaussian Process Regression," Advances in Neural Information Processing Systems, MIT Press, 2005.
[22] K.I. Kim and Y. Kwon,, "Example-Based Learning for Single Image Super-Resolution and JPEG Artifact Removal," Max-Planck Institut für Biologische Kybernetik, Technical Report 173, http://www.kyb.mpg.de/ publications/attachments TechReport-173_[0].pdf, Aug. 2008.
[23] S. Haykin, Neural Networks: A Comprehensive Foundation, second ed. Prentice Hall, 1999.
[24] Z. Lin and H.-Y. Shum, "Fundamental Limits of Reconstruction-Based Superresolution Algorithms under Local Translation," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 1, pp. 83-97, Jan. 2004.
6 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool