Single Image Super-Resolution Method via Refined Local Learning

doi:10.1007/s12204-015-1583-1

上海交通大学学报（英文版） ›› 2015, Vol. 20 ›› Issue (1): 26-31.doi: 10.1007/s12204-015-1583-1

Single Image Super-Resolution Method via Refined Local Learning

TANG Song-ze*(唐松泽), XIAO Liang (肖亮), LIU Peng-fei (刘鹏飞)

(School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing 210094, China)

出版日期:2015-02-28 发布日期:2015-03-10
通讯作者: TANG Song-ze*(唐松泽) E-mail:ts198708@163.com

Single Image Super-Resolution Method via Refined Local Learning

TANG Song-ze*(唐松泽), XIAO Liang (肖亮), LIU Peng-fei (刘鹏飞)

(School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing 210094, China)

Online:2015-02-28 Published:2015-03-10
Contact: TANG Song-ze*(唐松泽) E-mail:ts198708@163.com

摘要/Abstract

摘要：

In this paper, we propose a refined local learning scheme to reconstruct a high resolution (HR) face image from a low resolution (LR) observation. The contribution of this work is twofold. Firstly, multi-direction gradient features are extracted to search the nearest neighbors for each image patch, then the non-negative matrix factorization (NMF) is used to reduce the complexity in weight calculation, and the initial HR embedding is estimated from the training pairs by preserving local geometry. Secondly, a global reconstruction constraint and post-processing by non-local filtering is incorporated into super-resolution (SR) reconstruction process to reduce the image artifacts and further improve the image visual quality. Experimental results show that the proposed algorithm improves the SR performance both in subjective and objective assessments compared with several existing methods.

关键词: refined local learning, neighbor embedding, multi-direction, non-negative matrix factorization (NMF), post-processing

Abstract:

Key words: refined local learning, neighbor embedding, multi-direction, non-negative matrix factorization (NMF), post-processing

中图分类号:

TP 319

TANG Song-ze*(唐松泽), XIAO Liang (肖亮), LIU Peng-fei (刘鹏飞). Single Image Super-Resolution Method via Refined Local Learning[J]. 上海交通大学学报（英文版）, 2015, 20(1): 26-31.

TANG Song-ze*(唐松泽), XIAO Liang (肖亮), LIU Peng-fei (刘鹏飞). Single Image Super-Resolution Method via Refined Local Learning[J]. Journal of shanghai Jiaotong University (Science), 2015, 20(1): 26-31.

参考文献 20

[1]	Borman S, Strevenson R L. Super-resolution from image sequences: A review [C]//Proceeding of 41st IEEE Computer Society Midwest Symposium on Circuits and Systems. Indiana, USA: IEEE, 1998: 374-378.
[2]	Park S C, Park M K, Kang M G. Super-resolution image reconstruction: A technical overview [J]. IEEE Signal Processing Magazine, 2003, 20 (3): 21-36.
[3]	Baker S, Kanade T. Limits on super-resolution and how to break them [J]. IEEE Transactions on Pattern Analysis Machine Intelligence, 2003, 24(9): 1167-1183.
[4]	Freeman W T, Pasztor E C, Carmichael O T.Learning low-level vision [J]. International Journal of Computer Vision, 2000, 40(1): 25-47.
[5]	Freeman W T, Jones T R, Pasztor E C. Examplebased super-resolution [J]. IEEE Computer Graphics and Applications, 2002, 22(2): 56-65.
[6]	Chang H, Yeung D Y, Xiong Y M. Super-resolution through neighbor embedding [C]//Proceedings of 17th IEEE Computer Society Conference on Computer Vision Pattern Recognition. Washington, DC, USA:IEEE, 2004: 275-282.
[7]	Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding [J]. Science, 2002,290(5500): 2323-2326.
[8]	Geng B, Tao D C. Ensemble manifold regularization [C]//Proceedings of 22nd IEEE Computer Society Conference on Computer Vision Pattern Recognition.Miami, FL: IEEE, 2009: 2396-2402.
[9]	Li X L, Lin S, Yan S C, et al. Discriminant locally linear embedding with high-order tensor data [J]. IEEE Transactions on Systems, Man, and Cybernetics: Part B, 2008, 38(2): 342-352.
[10]	Zhou T Y, Tao D C, Wu X D. Manifold elastic net:A unified framework for sparse dimension reduction [J]. Data Mining Knowledge Discovery, 2011, 22(3):340-371.
[11]	Shan Q, Li Z R, Jia J Y, et al. Fast image/video upsampling [J]. ACM Transactions on Graphics, 2008,27(5): 1-8.
[12]	Tang Y, Yan P K, Yuan Y, et al. Single-image superresolution via local learning [J]. International Journal of Machine Learning and Cybernetics, 2011, 2 (1): 15-23.
[13]	Su K, Tian Q, Xue Q, et al. Neighborhood issue in single-frame image super-resolution [C]//Proceedings of 6th IEEE International Conference on Multimedia and Expo. Amsterdam, the Netherlands: IEEE, 2005:1122-1125.
[14]	Coomans D, Massart D L. Alternative K-nearest neighbor rules in supervised pattern recognition. Part 1. K-nearest neighbor classification by using alternative voting rules [J]. Analytica Chimica Acta, 1982,136: 15-27.
[15]	Lee D D, Seung H S. Algorithms for non-negative matrix factorization [M]. Cambridge, MA, USA: MIT Press, 2001.
[16]	Liu Wei-xiang, Zheng Nan-ning, You Qu-bo. Nonnegative matrix factorization and its applications in pattern recognition [J]. Chinese Science Bulletin, 2006,51(3): 241-250 (in Chinese).
[17]	Yang J C,Wright J, Huang T S, et al. Image superresolution via sparse representation [J]. IEEE Transactions on Image Processing, 2010, 19(11): 1-8.
[18]	Buades A, Coll B, Morel J M. Nonlocal image and movie denoising [J]. International Journal of Computer Vision, 2008, 76(2): 123-139.
[19]	Chan T M, Zhang J P, Pu J, et al. Neighbor embedding based super-resolution algorithm through edge detection and feature selection [J]. Pattern Recognition Letters, 2009, 30(5): 494-502.
[20]	Zhang K B, Gao X B, Li X L, et al. Partially supervised neighbor embedding for example-based image super-resolution [J]. IEEE Journal of Selected Topics in Signal Processing, 2011, 5(2): 230-238.

Single Image Super-Resolution Method via Refined Local Learning

Single Image Super-Resolution Method via Refined Local Learning

可视化

摘要/Abstract

引用本文

使用本文

参考文献 20

相关文章 1

编辑推荐

Metrics

本文评价