计算机科学 ›› 2018, Vol. 45 ›› Issue (3): 253-257.doi: 10.11896/j.issn.1002-137X.2018.03.040
许影,李强懿
XU Ying and LI Qiang-yi
摘要: 通过分析二值图像发现其像素值具有稀疏特性,因此采用L0梯度反卷积算法结合二值图像的组合特性来处理盲二值图像的复原问题。常见的图像复原方法均将二值图像看作灰度值图像来处理,当其考虑到二值图像的特殊性质时,将会针对这种特定类型的图像得到更好的复原效果。提出的盲复原算法基于一阶梯度空间L0最小化问题的框架,利用L0梯度图像平滑方法来获得明显的图像边缘以估计模糊核,并将二值图像的特有属性作为正则项加入目标函数。在图像的复原过程中,通过二值图像先验来强制复原结果趋于二值图像。根据提出的模型,给出了基于稀疏特性的盲二值图像复原算法。通过实验将该算法与传统的盲反卷积复原算法进行比较,结果表明所提算法具有良好的性能,对二值图像进行复原是有效的。
[1] PENTLAND A P.A New Sense for Depth of Field [J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1987,9(4):523-531. [2] MONTEFUSCO L B,LAZZARO D.An Iterative-Based ImageRestoration Algorithm with an Adaptive Parameter Estimation [J].IEEE Transactions on Image Processing a Publication of the IEEE Signal Processing Society,2012,21(4):1676-1686. [3] HAMIDI A E,MNARD M,LUGIEZ M,et al.Weighted andextended total variation for image restoration and decomposition [J].Pattern Recognition,2010,43(4):1564-1576. [4] PATIL M.An Efficient Method of Detecting Exudates in Diabetic Retinopathy:Using Texture Edge Features[C]∥International Conference on Advances in Computing,Communications and Informatics.2016. [5] WANG M,CHEN Y,WANG X.Recognition of HandwrittenCharacters in Chinese Legal Amounts by Stacked Autoencoders[C]∥International Conference on Pattern Recognition.IEEE,2014:3002-3007. [6] SCHONFELD D,GOUTSIAS J.Optimal morphological pattern restoration from noisy binary images [J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1991,13(1):14-29. [7] CHEN R,LIU X,ZOU M.Binary Image Restoration Based on MRF [J].Journal of Image & Graphics,1999,47(7):1038-1045. [8] WANG Y,YANG J,YIN W,et al.A New Alternating Minimization Algorithm for Total Variation Image Reconstruction [J].Siam Journal on Imaging Sciences,2008,1(3):248-272. [9] ZHANG J.An Alternating Minimization Algorithm for BinaryImage Restoration [J].IEEE Transactions on Image Proces-sing,2012,21(21):883-888. [10] HRADIS M,KOTERA J,ZEMˇK P,et al.Convolutional Neural Networks for Direct Text Deblurring[C]∥British Machine Vision Conference.2015. [11] DONG C,LOY C C,HE K,et al.Image Super-Resolution Using Deep Convolutional Networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2016,38(2):295-307. [12] LIU N,ZHENG X,SUN H,et al.Two-dimensional bar codeout-of-focus deblurring via the Increment Constrained Least Squares filter[J].Pattern Recognition Letters,2013,34(2):124-130. [13] MEI X,QI H,HU B G,et al.Improving image restoration with soft-rounding [C]∥Proceedings of the IEEE International Conference on Computer Vision.2015:459-467. [14] FANG L,LIU H,WU F,et al.Separable Kernel for Image Deblurring [C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2014:2885-2892. [15] PAN J,HU Z,SU Z,et al.Deblurring text images via 10-regula-rized intensity and gradient prior [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2014:2901-2908. [16] XU L,LU C,XU Y,et al.Image smoothing via L 0,gradient minimization [J].Acm Transactions on Graphics,2011,30(6):61-64. [17] ZHAO Z G,CHEN Y Y,ZHAO Y,et al.Motion deblurring based on edge prior model [J].Computer Science,2015,42(5):305-308.(in Chinese) 赵志刚,陈莹莹,赵毅,等.基于边缘先验模型的运动去模糊[J].计算机科学,2015,42(5):305-308. [18] XU L,ZHENG S,JIA J.Unnatural l0 sparse representation for natural image deblurring [C]∥Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition.2013:1107-1114. [19] PERRONE D,FAVARO P.Total Variation Blind Deconvolu-tion:The Devil Is in the Details [C]∥IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2014:2909-2916. |
No related articles found! |
|