Journal Title : International Journal of Modern Trends in Engineering and Science
Paper Title : IMAGE SUPER RESOLUTION USING SPARSE REPRESENTATION
Volume 03 Issue 07 2016
ISSN no: 2348-3121
Page no: 240-242
Abstract – Single image super resolutions a model and dynamic image processing problem, which object is to generate a high-resolution (HR) image from a low-resolution input image. A sparse representation for each patch of the low – resolution input and uses the coefficients of this representation to generatethehigh resolution output. By joining two dictionaries of the low and high resolution image patches, it can enforce the similarity of sparse representations between the low resolution and high resolution image patch pair with respect to their own dictionaries.Thesparse representation of a low resolution image patch can be functional with the high resolution image patch dictionary to generate a super resolution image .This algorithm generates high–resolution images that are competitive or superior in quality to images produced by other SR methods. This approach is logically robust to noise and can handle super resolution with noisy inputs in a more combined edge work.
Keywords— Single image super-resolution, Markov Random field, Image patch pairs, Sparse Representation
- Yi Xu, Xiao kang Yang and Truong Q. Nguyen, “Single Image Super resolution Based on Gradient Profile Sharpness” IEEE Trans. Image Process., Oct 2015.
- T. Peleg and M. Elad, “A statistical prediction model based on sparse representations for single image super-resolution” IEEE Trans. Image Process., Jun. 2014.
- W. Dong, L. Zhang, R. Lukac, and G. Shi, “Sparse representation based image interpolation with nonlocal autoregressive modeling” IEEE Trans.Image Process., Apr. 2013.
- K. Zhang, X. Gao, D. Tao, and X. Li, “Multi-scale dictionary for single image super-resolution” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2012.
- J. Sun, J. Sun, Z. Xu, and H.-Y. Shum, “Gradient profile prior and its applications in image super-resolution and enhancement” IEEE Trans. Image Process. Jun. 2011.