A Patch Ordering Approach to Single Image Super-resolution Problem

  • Vahid Anari Department of Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University,
  • Farbod Razzazi Department of Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University,
  • Rasoul Amirfattahi Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan
Keywords: Dictionary learning, Sparse representation, Super resolution, Patch ordering.

Abstract

In this paper, we propose a novel patch ordering approach to single image super-resolution (SR) algorithm which is called as patch ordering approach to single image super resolution (POSR). We aimed at selecting more informative high-resolution (HR) and low-resolution (LR) patches for single image SR algorithms based on sparse representation and dictionary learning. Our proposed POSR algorithm, first ordered HR and LR patches for each training images based on minimization of total variation measure (TV). Then, it assigned a sampling step for patch selection in each image. In this way, training patches were extracted based on image texture complexity. This leads to training dictionaries with the high and low resolution more efficiently. Unlike other methods which have used additional restrictions in high resolution image reconstruction phase, the proposed method, has only used the basic assumption of sparse representation super resolution. The experimental results for quantitative criteria (PSNR, RMSE, SSIM and elapsed time), human observation as a qualitative measure and computational complexity verify the improvements offered by the proposed POSR algorithm.

References

[1] Dai S, Han M.,Xu W, et al. (2007) Soft edge smoothness prior for alpha channel super resolution. In: Proceeding of the 2007 IEEE Conf. Computer Vision and Pattern Recognition, pp.1-8
[2] Sun J, Xu Z, Shum H (2008) Image super-resolution using gradient profile prior. In: Proceeding of the 2008 IEEE Conf. Computer Vision and Pattern Recognition, pp.1-8
[3] Chen H, Jiang B, Chen B (2011) Image super-resolution based on patches structure. In: Proceeding of the 2011 IEEE International Congress Image and Signal Processing, pp. 1076-1080
[4] Farsiu S, Robinson M. D, Elad M, et al. (2004) Fast and robust multi-frame super resolution. IEEE Trans. Image Process. , 13(10): pp. 1327-1344
[5] Hardie R.C, Barnard K.J, Armstrong E.E (1997) Joint MAP registration and high-resolution image estimation using a sequence of under sampled images. IEEE Trans. Image Process. 6(12): pp. 1621-1633.6
[6] Jiang J, Hu R, Han, Z, et al. (2014) Efficient single image super-resolution via graph-constrained least squares regression. Multimedia Tools and Applications, 72(3),: pp. 2573-2596
[7] Suresh K.V, Rajagopalan A (2006) A discontinuity adaptive method for super-resolution of license plates. Computer Vision, Graphics and Image Process. pp. 25-34
[8] Freeman W.T, Jones T.R, Pasztor E.C (2002) Example-based super-resolution. IEEE Computer graphics and Applications 22(2): pp. 56-65
[9] Gao X, Zhang, K, Tao D, Li X (2012) Image super-resolution with sparse neighbor embedding. IEEE Trans. of Image Process. 21(7): pp. 3194-3205
[10] Yang J, Wang Z, Lin Z, Cohen S, Huang T (2012) Coupled Dictionary Training for Image Super-Resolution. IEEE Trans. Image Process. 21(8): pp. 3467-3478
[11] Yang J, Wright J, Huang T, Ma Y (2008) Image super-resolution as sparse representation of raw image patches. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8
[12] Yang J, Wright J, Huang T, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans. on image Process.19(11): pp. 2861-2873
[13] Zeyde R, Elad M, Protter M, (2012)On single image scale-up using sparse-representations. Lecture Notes in Computer Science, 69(20): pp. 711-730
[14] Aharon M, Elad M, Bruckstein A (2006) A K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation. IEEE Trans. on Signal Process, 54(11): pp. 4311-4322
[15] Cao F, et al. (2016) Image Super-Resolution via Adaptive l_p (o [16] Gong W, HU L, Li J, Li W (2015) Combining sparse representation and local rank constraint for single image super resolution. Information Sciences, 325. pp. 1-19
[17] Han N, Song Z, Li Y (2016) Cluster-based image super-resolution via jointly low-rank and sparse representation', Journal of Visual Communication and Image Representation, 38: pp. 175-185
[18] Wang S, Zhang L, Liang Y, Pan Q (2012) Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis. In: proceeding of the IEEE Conf. Computer Vision and Pattern Recognition, pp. 2216-2223
[19] Liu D, Wang Z, Wen B, Yang J, Han W (2016) Huang, T. Robust single image super-resolution via deep networks with sparse prior. IEEE Trans. on Image Process. 25(7): pp. 3194-3207
[20] Yeganli F, Nazzal M, Unal M, Ozkaramanli H (2012) Image super-resolution via sparse representation over coupled dictionary learning based on patch sharpness. In: Proceeding of the IEEE European Modelling Symposium, pp.203-208
[21] Chao G, Bo J, Ai-xin Z (2013) MCA-based Image Super Resolution. Communications Technology, 3:pp. 20-27
[22] Jiang J, Yang J, Pan Z (2016) Super-resolution reconstruction based on structure tensor's eigenvalue and classification dictionary. In: Proceeding of the Int. Conf. on in Audio, Language and Image Processing, pp. 452-456
[23] Liu M, Chen X, Wang X (2015) Latent fingerprint enhancement via multi-scale patch based sparse representation. IEEE Trans. on Information Forensics and Security, 10(1): pp. 6-15.24
[24] Zhang H, Liu W, Liu J, Liu C, Shi C (2018) Sparse representation and adaptive mixed samples regression for single image super-resolution. Signal Process: Image Communication. 67: pp. 79-89
[25] Lu W, Sun H, Wang R, He L, Jou M, Syu S, Li J (2017) Single image super resolution based on sparse domain selection. Neurocomputing. 269: pp. 180-187.
[26] Naderahmadian Y, Beheshti S, Tinati M. A (2016) Correlation based online dictionary learning algorithm. IEEE Trans. on Signal Process. 64(3): pp. 592-602
[27] Zhu X, Tao J, Li B, Chen X, Li Q (2015) A novel image super-resolution reconstruction method based on sparse representation using classified dictionaries. In: Proceeding of the IEEE International Conference on Information and Automation, pp.776-780
[28] Yang W, Yuan T, Wang W, Zhao F, Liao Q (2017) Single-Image Super-Resolution by Subdictionary Coding and Kernel Regression. IEEE Trans. on Systems, Man and Cybernetics: Systems, 47(9): p. 2478-2488
[29] Juefei-Xu F, M Savvides (2015) Single face image super-resolution via solo dictionary learning. In: Proceeding of the IEEE International Conference on Image Processing (ICIP), pp. 2239-2243
[30] Ram I, Elad M, Cohen I (2013) Image processing using smooth ordering of its patches', IEEE Trans. on Image Process. 22(7): pp. 2764-2774
[31] Cormen T.H. (2009) Introduction to algorithms (2nd ed.) MIT press
[32] Pati Y.C, Rezaiifar R, Krishnaprasad P.S (1993) Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition. In: Proceedings of 27th Asilomar Conference on Signals, Systems and Computers, pp. 40-44.27
[33] Timofte R, De Smet V, Van Gool L (2013) Anchored neighborhood regression for fast example-based super-resolution.In: Proceeding of the IEEE International Conference on Computer Vision, Sydney, pp. 1920-1927
Published
2019-12-01
How to Cite
Anari, V., Razzazi, F., & Amirfattahi, R. (2019). A Patch Ordering Approach to Single Image Super-resolution Problem. Majlesi Journal of Electrical Engineering, 13(4), 123-134. Retrieved from http://mjee.org/index/index.php/ee/article/view/3257
Section
Articles