计算机科学 ›› 2017, Vol. 44 ›› Issue (Z11): 169-174.doi: 10.11896/j.issn.1002-137X.2017.11A.035
秦绪佳,单扬洋,肖佳吉,郑红波,张美玉
QIN Xu-jia, SHAN Yang-yang, XIAO Jia-ji, ZHENG Hong-bo and ZHANG Mei-yu
摘要： 针对依靠外部图像库的超分辨率(SR)重建算法训练耗时长、容易出现错误高频细节的问题,提出了一种基于压缩感知(CS)理论和支持向量回归(SVR)的单幅图像超分辨率重建方法。对降质图像本身训练SVR模型,充分挖掘图像自身的自相似特点。训练过程中先对输入图像边缘进行检测并对图像块进行分类,然后稀疏编码图像块,再根据图像的标签向量和稀疏表示矩阵训练得到SVR模型,并在测试过程中利用该模型预测高分辨率(HR)图像。实验结果表明,与基于外部库方法重建图像的方法相比,该算法所得结果的细节更加真实；与双三次插值方法相比该算法所得结果的边缘更加清晰。
| [1] LIN Z C,SHUM H Y.Fundamental limits of reconstruction-based super-resolution algorithms under local translation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(1):83-97. [2] YANG J C,WRIGHT J,HUANG T.Image super-resolution as sparse representation of raw image patches[C]∥Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition.Alaska:IEEE Computer Press,2008:1-8. [3] FREEMAN W T,PASZTOR E C,CARMICHAEL O T.Learning low-level vision[J].International Journal of Computer Vision,2000,40(1):25-47. [4] DAI S,HAN M,XU W,et al.Soft edge smoothness prior for alpha channel super resolution[C]∥Proceedings of IEEE International Conference on Computer Vision.Washington,DC:IEEE Computer Press,2007:5-8. [5] DURARLE M F,DAVENPORT M A.Single-Pixel Imaging via Compressive Sampling[J].IEEE Signal Processing Magazine,2008,25(2):83-91. [6] YANG M C,WANG Y C F.A Self-Learning Approach to Single Image Super-Resolution[J].IEEE Transactions on Multimedia,2013,15(3):498-508. [7] ZHANG K B,GAO X B,TAO D C.Multi-scale dictionary for single image super-resolution[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Alaska,IEEE Computer Press,2012:1114-1121. [8] YU G S,GUILLERMO S,STPHANE M.Solving Inverse Pro-blems With Piecewise Linear Estimators:From Gaussian Mixture Models to Structured Sparsity[J].IEEE Transactions on Image Processing,2012,21(5):2418-2499. [9] PELEG T,ELAD M.A Statistical Prediction Model Based on Sparse Representations for Single Image Super-Resolution[J].IEEE Transacations on Image Processing,2014,23(6):2569-2582. [10] LI D L,MERSEREAU R M,SIMSKE S J.Blind Image Deconvolution Using Support Vector Regression[C]∥Proceedings IEEE International Conference on Acoustics,Speech and Signal Process.Washington,DC:IEEE Computer Press,2005:113-116. [11] LI D L,RUSSELL S S.Single Image super-resolution based on support vector regression[C]∥Proceedings of International Joint Conference on Neural Networks.Washington,DC:IEEE Computer Press,2006:2898-2901. [12] YANG M C,CHU C T,WANG YC F.Learning Sparse Image Representation With Support Vector Regression For Single Image Super Resolution[C]∥IEEE International Conference on Image Processing.Washington,DC:IEEE Computer Press,2010:1973-1976. [13] GLASNER D,BAGON S,IRANI M.Super-Resolution From a Single Image[C]∥Proceedings of 2009 IEEE 12th International Conference on Computer Vision.Kyoto:IEEE Computer Press,2009:349-356. [14] ZONTAK M,IRANI M.Internal Statistics of a Single Natural Image[C]∥Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition.America:Colorado Springs,2011:977-984. [15] MAIRAL J,BACH F,PONCE J.Online Learning for Matrix Factorization and Sparse Coding[J].Journal of Machine Lear-ning Theory,2010,11(1):19-60. [16] TAPPEN M F,RUSSELL B C,FREEMAN W T.Exploiting the Sparse Derivative Prior for Super-Resolution and Image Demosaicing[C]∥proceedings of IEEE workshop on Statistical and Computational Theories of Vision.Fort Collins:IEEE Computer Press,2003:1-24. [17] EFRON B,HASTIE T,JOHNSTONE I.Least Angle Regression[J].The Annals of Statistics,2004,32(2):407-499. |
| No related articles found! |
|
||
首页