Browse > Article
http://dx.doi.org/10.6109/jkiice.2014.18.12.2946

Super Resolution by Learning Sparse-Neighbor Image Representation  

Eum, Kyoung-Bae (Department of Computer and Information Engineering, Kunsan National University)
Choi, Young-Hee (Department of Computer and Information Engineering, Kunsan National University)
Lee, Jong-Chan (Department of Computer and Information Engineering, Kunsan National University)
Publication Information
Journal of the Korea Institute of Information and Communication Engineering / v.18, no.12, 2014 , pp. 2946-2952 More about this Journal
Abstract
Among the Example based Super Resolution(SR) techniques, Neighbor embedding(NE) has been inspired by manifold learning method, particularly locally linear embedding. However, the poor generalization of NE decreases the performance of such algorithm. The sizes of local training sets are always too small to improve the performance of NE. We propose the Learning Sparse-Neighbor Image Representation baesd on SVR having an excellent generalization ability to solve this problem. Given a low resolution image, we first use bicubic interpolation to synthesize its high resolution version. We extract the patches from this synthesized image and determine whether each patch corresponds to regions with high or low spatial frequencies. After the weight of each patch is obtained by our method, we used to learn separate SVR models. Finally, we update the pixel values using the previously learned SVRs. Through experimental results, we quantitatively and qualitatively confirm the improved results of the proposed algorithm when comparing with conventional interpolation methods and NE.
Keywords
Super Resolution; Sparse-Neighbor Image Representation; Support Vector Regression;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 J. M. Lim and J. Yoo, "Super resolution algorithm using discrete wavelet transform for single image," Journal of the Society of Broadcast Engineering, vol. 17, no. 2, 2012.
2 S. Park, M. Park, and M. Kang, "Super-resolution image reconstruction : A technical overview," IEEE Signal Processing Magazine, vol.20, pp.2136, 2003.
3 H. Kang and J. Jeon, "Texture mapping using bilinear interpolation," Proceeding of Korea Information Science Society, vol. 26, no. 1, pp. 644-646, 1999.
4 W. Freeman, T. Jones, and E. Pasztor, "Example based super resolution," IEEE Computer Graphics and Applications, vol. 22, no. 2, 2002.
5 M. Yang, C. Chu, and Y. F. Wang, "Learning sparse image representation with support vector regression for single image super resolution," in Proceeding of ICIP, 2010.
6 H. Chang, D. Yeung, and Y. Xiong, "Super resolution through neighbor embedding," in Proceeding of IEEE CVPR, vol. 1, 2004.
7 V. Vapnik, Statistical Learning Theory, Wiley Interscience, 1998.
8 Chih-Chung Chang and Chih-Jen Lin, LIBSVM: a library for support vector machines, 2001.
9 H. Shin, S. D. Chung, B. H. Ku, and H. Ko, "Local block learning based super resolution for license plate," Journal of the Korea Society of Computer and Information Science, vol. 16, no. 1, 2011.