计算机科学 ›› 2018, Vol. 45 ›› Issue (4): 312-318.doi: 10.11896/j.issn.1002-137X.2018.04.053
• 图形图像与模式识别 • 上一篇
李键红,吴亚榕,吕巨建
LI Jian-hong, WU Ya-rong and LV Ju-jian
摘要： 基于稀疏表示的图像超分辨率重建算法以近似随机抽取的方式选取字典中的原子来拟合图像片,而实际中的字典原子的选择体现出了很强的结构稀疏性,从而导致算法计算复杂且引入了大量的误差,影响重建图像的质量。针对该问题,提出了一种基于组稀疏表示的在线图像超分辨率重建算法。该方法引入组稀疏理论,仅利用输入的低分辨率图像作为样本来构建组稀疏字典,通过结合组稀疏性和几何对偶性来构建超分辨率图像算法的成本函数,并使用提出的一种迭代的方法进行求解。实验表明,该算法在视觉观察和参数比较上都优于当前主流的超分辨率算法。
| [1] LI X,ORCHARD M T.New edge-directed interpolation[J].IEEE Transactions on Image Processing,2001,10(10):1521-1527. [2] SHAN Q,LI Z R,JIA J Y,et al.Fast image/video upsampling[C]∥ACM Transactions on Graphics.2008. [3] TAI Y W,LIU S,BROWN M S,et al.Super resolution using edge prior and single image detail synthesis[C]∥Computer Vision and Pattern Recognition.2010:2400-2407. [4] ZHANG K,GAO X,TAO D,et al.Single image super-resolution with multiscale similarity learning[J].IEEE Transactions on Neural Networks & Learning Systems,2013,24(10):1648-1659. [5] SUN J,XU Z,et al.Gradient profile prior and its applications in image super-resolution and enhancement[J].IEEE Transactions on Image Processing,2011,20(6):1529-1542. [6] CHANG H,YEUNG D Y,XIONG Y.Super-Resolution through Neighbor Embedding[C]∥Computer Vision and Pattern Recognition.2004:275-282. [7] YANG J,WRIGHT J,HUANG T,et al.Image super-resolution as sparse representation of raw image patches[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Re-cognition.2008:1-8. [8] YANG J,WRIGHT J,HUANG T S,et al.Image super-resolution via sparse representation[J].IEEE Transactions on Image Processing,2010,19(11):2861-2873. [9] YANG J,WANG Z,LIN Z,et al.Coupled Dictionary Training for Image Super-Resolution[J].IEEE Transactions on Image Processing,2012,21(8):3467-3478. [10] DONG W,ZHANG L,SHI G,et al.Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regu-larization[J].IEEE Transactions on Image Processing,2010,20(7):1838-1857. [11] LU J,SUN Y.Context-aware single image super-resolutionusing sparse representation and cross-scale similarity[J].Signal Processing Image Communication,2015,32(C):40-53. [12] LI J,GONG W,LI W.Dual-sparsity regularized sparse representation for single image super-resolution[J].Information Scie-nces,2015,298(C):257-273. [13] YU J,GAO X,TAO D,et al.A unified learning framework for single image super-resolution[J].IEEE Transactions on Neural Networks & Learning Systems,2014,25(4):780-792. [14] HE H,SIU W C.Single image super-resolution using Gaussian process regression[C]∥Computer Vision and Pattern Recognition.2011:449-456. [15] GLASNER D,BAGON S,IRANI M.Super-resolution from asingle image[C]∥International Conference on Computer Vision.2009:349-356. [16] ZONTAK M,MOSSERI I,IRANI M.Separating Signal from Noise Using Patch Recurrence across Scales[C]∥Computer Vision and Pattern Recognition.2013:1195-1202. [17] CAI T T,WANG L.Orthogonal Matching Pursuit for Sparse Signal Recovery with Noise[J].IEEE Transactions on Information Theory,2011,57(7):4680-4688. [18] AHARON M,ELAD M,BRUCKSTEIN A.K-SVD:An Algo-rithm for Designing Overcomplete Dictionaries for Sparse Representation[J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322. [19] MAJUMDAR A,WARD R K.Fast Group Sparse Classification[C]∥IEEE Pacific Rim Conference on Communications,Computers and Signal Processing.2009:11-16. |
| No related articles found! |
|
||
首页