基于稀疏特性的盲二值图像去模糊

doi:10.11896/j.issn.1002-137X.2018.03.040

摘要/Abstract

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。

关键词: 盲图像复原,L₀范数,二值图像,正则化,模糊核估计

Abstract: Analysis of binary image shows that the pixel values of binary image are sparse,hence the L₀ gradient deconvolution is combined with the combinatorial property to deal with the blind binary image restoration problem.Common image restoration methods treat binary image as gray-scale image with an optional threshold,when considering the special property of the binary image,they will get better recovery results for this particular type of image.The proposed blind image restoration algorithm is based on the frame of the first-order gradient space L₀ minimization program,uses the L₀ gradient image smoothing method to obtain distinct image edges to estimate the blurring kernel,and introduces the special binary property of binary image into the objective function as a regularizer.The binary image prior is used in the restoration process to force the latent restored image to be binary.According to the proposed model,the blind binary image deconvolution algorithm based on the sparse property was presented.The experimental results show that compared with conventional blind deconvolution algorithms,the proposed method has more favorable performance,and is more efficient for binary image restoration.

Key words: Blind image restoration,L₀ norm,Binary image,Regularization,Kernel estimation

许影,李强懿. 基于稀疏特性的盲二值图像去模糊[J]. 计算机科学, 2018, 45(3): 253-257. https://doi.org/10.11896/j.issn.1002-137X.2018.03.040

XU Ying and LI Qiang-yi. Blind Binary Image Deconvolution Based on Sparse Property[J]. Computer Science, 2018, 45(3): 253-257. https://doi.org/10.11896/j.issn.1002-137X.2018.03.040

参考文献

[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,MNARD 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,ZEMˇK 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.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed