Abstract
Nearest neighbor-based algorithms are popular in example-based super-resolution from a single image. The core idea behind such algorithms is that similar images are close in the sense of distance measurement. However, it is well known in the field of machine learning and statistical learning theory that the generalization of the nearest neighbor-based estimation is poor, when complex or high dimensional data are considered. To improve the power of the nearest neighbor-based algorithms in single-image based super-resolution, a local learning method is proposed in this paper. Similar to the nearest neighbor-based algorithms, a local training set is generated according to the similarity between the training samples and a given test sample. For super-resolving the given test sample, a local regression function is learned on the local training set. The generalization of nearest neighbor-based algorithms can be enhanced by the process of local regression. Based on such an idea, we propose a novel local-learning-based algorithm, where kernel ridge regression algorithm is used in local regression for its well generalization. Some experimental results verify the effectiveness and efficiency of the local learning algorithm in single-image based super-resolution.
Similar content being viewed by others
References
Tsai R, Huang T (1984) Multi-frame image restoration and registration. Adv Comput Vis Image Process 1:317–339
Li X, Hu Y, Gao X, Tao D, Ning B (2010) A multi-frame image super-resolution method. Signal Process 90(2):405–414
Li X, Orchard MT (2001) New edge-directed interpolation. IEEE Trans Image Process 10(10):1521–1527
Unser M (1999) Splines: a perfect fit for signal and image processing. IEEE Signal Process Mag 16(6):22–38
Elad M (2002) On the origin of the bilateral filter and ways to improve it. IEEE Trans Image Process 11(10):1141–1151
Hardie R (2007) A fast image super-resolution algorithm using an adaptive wiener filter. IEEE Trans Image Process 16(12):2953–2964
Tschumperlé D, Deriche R (2005) Vector-valued image regularization with pdes: a common framework for different applications. IEEE Trans Pattern Anal Mach Intell 27(4):506–517
Dai S, Han M, Xu W, Gong Y (2007) Soft edge smoothness prior for alpha channel super resolution. In: Proc. IEEE ICIP’07, pp 1–8
Roweis S, Saul L (2000) Nonlinear dimensionality reduction by locally linear embedding. Sci Agric 290(5500):2323–2326
Scholkopf B, Smola A (2002) Learning with kernels. MIT Press, Cambridge
Kim K, Kwon Y (2010) Single-image super-resolution using sparse regression and natural image prior. IEEE Transa Pattern Anal Mach Intell 32(6):1127–1133
Yang J, Wright J, Huang T, Ma Y (2008) Image super-resolution as sparse representation of raw image patches. In: Proc. IEEE CVPR’08, June 2008, pp 1–8
Freeman W, Pasztor E, Carmichael O (1999) Learning low-level vision. In: The proceedings of the seventh IEEE international conference on computer vision, vol 2. pp 1182–1189
Freeman W, Jones T, Pasztor E (2002) Example-based super-resolution. IEEE Comput Graph Appl 22(2):56–65
Chang H, Yeung D, Xiong Y (2004) Super-resolution through neighbor embedding. In: Proc. IEEE CVPR’04, vol 1. pp 275–282
Ni K, Nquyen T (2007) Image superresolution using support vector regression. IEEE Trans Image Process 16(6):1596–1610
Pang Y, Yuan Y, Li X (2009) Iterative subspace analysis based on feature line distance. IEEE Trans Image Process 18(4):903–907
Bishop C, Blake A, Marthi B (2003) Super-resolution enhancement of video. In: Bishop CM, Frey B (eds) Proceedings of the ninth international workshop on artificial intelligence and statistics, Key West, FL, 3–6 January 2003
Pickup L, Robert S, Zisserman A (2003) A sampled texture prior for image super-resolution. In: Adv Neural Inf Process Syst 16, pp 1587–1594
Sun J, Tao H, Shum H (2003) Image hallucination with primal sketch priors. In: Proc IEEE CVPR’03, vol 2. pp II-729–II-736
Zhang T, Tao D, Li X, Yang J (2009) Patch alignment for dimensionality reduction. IEEE Trans Knowl Data Eng 21(9):1299–1313
Zhang K et al (2011) Partially supervised NE for example-based image super-resolution. IEEE J Sel Top Signal Process (to be published)
Li B, Chang H, Shan S, Chen X (2009) Locality preserving constraints for super-resolution with neighbor embedding. In: Proceedings of the IEEE ICIP’09, November 2009. pp 1189–1192
Zhou T, Tao D, Wu X (2011) Manifold elastic net: a unified framework for sparse dimension reduction. Data Mining Knowl Discov (to be published)
Smale S, Zhou D (2007) Learning theory estimates via integral operators and their approximation. Constr Approx 26:153–172
Shawe-Taylor J, Cristianini N. Kernel methods for pattern analysis. Cambridge University Press, Cambridge, July 2004
Vapnik V (1998) Statistical learning theory. Wiley, New York
Wu Q, Ying Y, Zhou D (2007) Multi-kernel regularized classifiers. J Complex 23(1):108–134
Cucker F, Zhou D (2007) Learning theory: an approximation theory viewpoint. Cambridge University Press, Cambridge
Smale S, Zhou D (2004) Shannon sampling and function reconstruction from point values. Bull Am Math Soc 41:279–305
Acknowledgments
The work presented in this paper is supported by the National Basic Research Program of China (973 Program) (Grant No. 2011CB707000), the National Natural Science Foundation of China (Grant No. 61072093) and the Open Project Program of the State Key Lab of CAD & CG (Grant No. A1116), Zhejiang University.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Tang, Y., Yan, P., Yuan, Y. et al. Single-image super-resolution via local learning. Int. J. Mach. Learn. & Cyber. 2, 15–23 (2011). https://doi.org/10.1007/s13042-011-0011-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-011-0011-6