Single image super resolution based on multiscale local similarity and neighbor embedding

Image quality and algorithm efficiency are the two core problems of super resolution (SR) from a single image. In this paper, we propose a novel single image SR method by using multiscale local similarity and neighbor embedding method. The proposed algorithm utilizes the self similarity redundancy in the original input image, and does not depend on external example images or the whole input image to search and match patches. Instead, we search and match patches in a localized region of the image in each level, which can improve the algorithm efficiency. The neighbor embedding method is used to generate more accurate patches for reconstruction. Finally, we use the original image and filters we design to control the iterate errors which caused by layered reconstruction, which can further improve the quality of SR results. Experimental results demonstrate that our method can ensure the quality of SR images and improve the algorithm efficiency.

[1]  Harry Shum,et al.  Gradient Profile Prior and Its Applications in Image Super-Resolution and Enhancement , 2011, IEEE Transactions on Image Processing.

[2]  Michal Irani,et al.  Super-resolution from a single image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[3]  Xuelong Li,et al.  Joint Learning for Single-Image Super-Resolution via a Coupled Constraint , 2012, IEEE Transactions on Image Processing.

[4]  Junping Zhang,et al.  An Improved Super-Resolution with Manifold Learning and Histogram Matching , 2006, ICB.

[5]  William T. Freeman,et al.  Example-Based Super-Resolution , 2002, IEEE Computer Graphics and Applications.

[6]  Stephen Lin,et al.  Super resolution using edge prior and single image detail synthesis , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  Zidong Wang,et al.  Image-Based Quantitative Analysis of Gold Immunochromatographic Strip via Cellular Neural Network Approach , 2014, IEEE Transactions on Medical Imaging.

[8]  Nan Zhang,et al.  A hybrid Wavelet Neural Network and Switching Particle Swarm Optimization algorithm for face direction recognition , 2015, Neurocomputing.

[9]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[10]  D. Yeung,et al.  Super-resolution through neighbor embedding , 2004, CVPR 2004.

[11]  Xuelong Li,et al.  Partially Supervised Neighbor Embedding for Example-Based Image Super-Resolution , 2011, IEEE Journal of Selected Topics in Signal Processing.

[12]  Xuelong Li,et al.  Color to Gray: Visual Cue Preservation , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Xuelong Li,et al.  Single Image Super-Resolution With Non-Local Means and Steering Kernel Regression , 2012, IEEE Transactions on Image Processing.

[14]  Fuad E. Alsaadi,et al.  Event-triggered H ∞ state estimation for discrete-time stochastic genetic regulatory networks with Markovian jumping parameters and time-varying delays , 2016, Neurocomputing.

[15]  Shuai Liu,et al.  Error-constrained reliable tracking control for discrete time-varying systems subject to quantization effects , 2016, Neurocomputing.

[16]  Roger Y. Tsai,et al.  Multiframe image restoration and registration , 1984 .

[17]  Truong Q. Nguyen,et al.  Single Image Superresolution Based on Gradient Profile Sharpness , 2015, IEEE Transactions on Image Processing.

[18]  Raanan Fattal,et al.  Image and video upscaling from local self-examples , 2011, TOGS.

[19]  Weidong Yan,et al.  Super-resolution from a single image based on local self-similarity , 2015, Multimedia Tools and Applications.

[20]  Chih-Yuan Yang,et al.  Exploiting Self-similarities for Single Frame Super-Resolution , 2010, ACCV.

[21]  Wenhan Yang,et al.  Image Super-Resolution Based on Structure-Modulated Sparse Representation , 2015, IEEE Transactions on Image Processing.

[22]  R. O. Lane,et al.  Non-parametric Bayesian super-resolution , 2010 .

[23]  M. Carter.  Computer graphics: Principles and practice , 1997 .

[24]  Fuad E. Alsaadi,et al.  Non-fragile state estimation for discrete Markovian jumping neural networks , 2016, Neurocomputing.

[25]  Xuelong Li,et al.  Greedy regression in sparse coding space for single-image super-resolution , 2013, J. Vis. Commun. Image Represent..

[26]  Xuelong Li,et al.  Single Image Super-Resolution With Multiscale Similarity Learning , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[27]  Stanley Osher,et al.  Image Super-Resolution by TV-Regularization and Bregman Iteration , 2008, J. Sci. Comput..

[28]  Xiaoqiang Lu,et al.  MR image super-resolution via manifold regularized sparse learning , 2015, Neurocomputing.

[29]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.