计算机科学 ›› 2017, Vol. 44 ›› Issue (11): 301-304.doi: 10.11896/j.issn.1002-137X.2017.11.046
刘小园,衣扬,杨磊,汪斌
LIU Xiao-yuan, YI Yang, YANG Lei and WANG Bin
摘要： 针对文档图像超分辨率重建问题,在传统双边全变差(Bilateral Total Variation,BTV)正则化超分辨率算法的基础上,提出了一种基于改进BTV的文档图像超分辨率算法。该算法引入一个新的正则项,即笔画宽度的方向,并根据字符笔画的局部宽度和局部方向自适应地进行平滑处理；然后通过分析输入的低分辨率图像及其插值,使输出图像的局部笔画宽度接近于局部的笔画方向。这种信息被压缩到基于笔画宽度的方向全变分正则项中。通过最小化正则项和数据保真项的线性组合,重建了高分辨率的图像。与相关的文档图像超分辨率方法相比,所提方法在视觉图像质量和字符识别精度方面得到了显著的改善。
| [1] REN F Q,QIU T S,HAN J,et al.Multi frame image superresolution reconstruction based on two order generalized total variation[J].Journal of Electronic Science,2015,43(7):1275-1280.(in Chinese) 任福全,邱天爽,韩军,等.基于二阶广义全变差的多帧图像超分辨率重建[J].电子学报,2015,43(7):1275-1280. [2] HE J X,REN H P,ZENG Q Y,et al.Super resolution recon-struction of weather radar echo based on improved total variation[J].Computer Simulation,2014,31(7):415-418.(in Chinese) 何建新,任红萍,曾强宇,等.基于改进全变差的天气雷达回波超分辨率重建[J].计算机仿真,2014,31(7):415-418. [3] ZHANG L,LIU Z M,TANG J.The realization of handwritten numeral recognition method based on BP neural network [J].Automation and Instrumentation,2015(6):169-170.(in Chinese) 张黎,刘争鸣,唐军.基于BP神经网络的手写数字识别方法的实现[J].自动化与仪器仪表,2015(6):169-170. [4] LI C F,YANG X,ZHANG X M,et al.Research on ultrasonic image denoising algorithm based on [J].MAP Journal of Electronic Science,2014(7):1291-1298.(in Chinese) 李春芳,杨鑫,张旭明,等.基于MAP的超声图像分解去噪算法研究[J].电子学报,2014(7):1291-1298. [5] YANG S F,ZHAO R Z.Research and development of image super resolution reconstruction based on low rank matrix and dictionary learning [J].Computer Research and Development,2016,53(4):884-891.(in Chinese) 杨帅锋,赵瑞珍.基于低秩矩阵和字典学习的图像超分辨率重建[J].计算机研究与发展,2016,53(4):884-891. [6] ABEDI A,KABIR E.Stroke width-based directional total variation regularisation for document image super resolution[J].Iet Image Processing,2015,10(2):158-166. [7] AYUBI S D,BAJWA U I,ANWAR M W.Super-ResolutionBased Enhancement of Cardiac MR Images[J].Current Medical Imaging Reviews,2015,11(999):1. [8] SHI F,CHENG J,WANG L,et al.LRTV:MR Image Super- Resolution With Low-Rank and Total Variation Regularizations[J].IEEE Transactions on Medical Imaging,2015,34(12):2459-2466. [9] RUDIN L,OSHER S,FATEMI E.Nonlinear total variationbased noise removel algorithms[J].Physical D Nonlinear Phenomena,1992,60(1-4):259-268. [10] FARSIU S,ROBINSON D.Fast and Robust Multiframe SuperResolution[J].IEEE Transactions on Image Processing,2004,13(10):1327-1344. [11] JIANG J,MA X,CAI Z,et al.Sparse Support Regression forImage Super-Resolution[J].IEEE Photonics Journal,2015,7(5):1-11. [12] CHU N,MOHAMMAD-DJAFARI A,PICHERAL J.RobustBayesian super-resolution approach via sparsity enforcing a priori for near-field aeroacoustic source imaging[J].Journal of Sound & Vibration,2013,2(18):4369-4389. [13] XIE J,FERIS R S,YU S S,et al.Joint Super Resolution andDenoising from a Single Depth Image[J].IEEE Transactions on Multimedia,2015,17(9):1525-1537. [14] SURYANARAYANA G,DHULI R.Simultaneous edge preserving and noise mitigating image super-resolution algorithm[J].AEU-International Journal of Electronics and Communications,2016,70(4):409-415. [15] XIANG H Y.Review of Super-resolution Image RestorationMethod[J].Journal of Chongqing University of Technology(Natural Science),2014,8(9):72-76.(in Chinese) 向海燕.超分辨率图像恢复方法综述[J].重庆理工大学学报(自然科学版),2014,28(9):72-76. |
| No related articles found! |
|
||
首页