计算机科学 ›› 2014, Vol. 41 ›› Issue (5): 299-303.doi: 10.11896/j.issn.1002-137X.2014.05.064

• 图形图像与模式识别 • 上一篇    下一篇

一种改进的小波域图像修复算法

胡文瑾,刘仲民,李战明   

  1. 西北民族大学数学与计算机科学学院 兰州730030;兰州理工大学电气工程与信息工程学院 兰州730050;兰州理工大学电气工程与信息工程学院 兰州730050
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金资助

Improved Algorithm for Image Inpainting in Wavelet Domains

HU Wen-jin,LIU Zhong-min and LI Zhan-ming   

  • Online:2018-11-14 Published:2018-11-14

摘要: 针对全变分小波图像修复算法在平滑区易产生阶梯效应并且噪声抑制不充分的缺陷,提出一种新颖的小波域图像修复模型。通过优化一个全变分和图像梯度的二范数的能量泛函来实现小波域的图像修复,使得在去除噪声的同时较好地保留了图像的边缘,在平滑区域削弱了阶梯效应,并利用有限差分法对所建立的扩散方程进行数值求解。实验结果表明:所提方法对于不同丢失比例的图像以及噪声图像都取得了较好的修复效果,尤其当小波系数丢失率较高时更为明显。

关键词: 图像修复,小波域,全变分模型,二次范数

Abstract: In view of staircase effect occurred in total variation minimization methods and insufficient noise suppression,a new wavelet-based image inpainting algorithm was presented in this paper.The inpainting processing performs with optimizing an energy function of total variational norm and the l2norm,and finite difference method is adopted for finally established diffusion equation.The scheme has strong capability of keeping sharp edge mean,and staircase effect is weakened in smooth area.Experimental results which use different image show that the proposed method achieves better inpainting effect,especially when the wavelet coefficient is relatively high.

Key words: Image inpainting,Wavelet domain,Total variational model,l2norm

[1] Bertalmio M,Sapiro G,Caselles V,et a1.2000.Image inpainting[C]∥ACM Proceedings of the 27th annual conference on Computer graphics and interactive techniques (SIGGRAPH).New York:ACM press,2000:417-424
[2] Chan T,Shen J.Mathematical models for local non-texture inpainting[J].SIAM Journal on Applied Mathematics,2002,62(3):1019-1043
[3] Chan T,Shen J.Non-Texture Inpainting by Curvature-driven Diffusions(CDD)[J].Journal of Visual Communication and Ima-ge Representation,2001,12(4):436-449
[4] 许建楼,冯象初,郝岩.改进的TV-Stokes 修复模型及其算法[J].电子与信息学报,2012,4(5):1142-1147
[5] Perez C P,Toyama K.Region filling and object removal by exemplar-based image inpainting[J].IEEE.Trans.Image Proces-sing,2004,13(9):1200-1212
[6] Sun J,Yaan L,Jia J,et al.Image completion with structurepropagation[J].ACM Transactions on Graphic,2005,24(3):861-868
[7] 孙玉刚,李开宇,程卫平,等.连续性约束下基于样例的图像修复算法[J].计算机应用研究,2011,28(5):1951-1953
[8] Elad M,Starck J-L,Querre P,et al.Simultaneous cartoon andtexture image inpainting using morphological component analysis (MCA)[J].Applied and Computational Harmonic Analysis,2005,19(3):340-358
[9] AujoI J F,Aubert C,Laure B F,et.al.Image decomposiiton:application to textured images and SAR imges[J].Scale Space Methods in Compute Vision,Lecture Notes in Computer Science 2003,2695:297-312
[10] Chan T F,Shen J,Zhou H-M.Total variation wavelet inpainting[J].J.Math.Imaging Vision,2006,25(1):107-125
[11] 张红英.数字图像修复技术的研究与应用[D].成都:电子科技大学,2006
[12] Wen You-wei,Chan R,Yip A M.A primal-dual method for total variation based wavelet domain inpainting [J].IEEE Transaction on Image Processing,2012,1(1):106-114
[13] Zhang Xiao-qun,Chan T F.Wavelet Inpainting by Nonlocal Total Variation[J].Inverse Problems and Imaging,2010,4(1):191-210
[14] 刘纯利,张弓.基于小波框架的盲图像修复研究[J].计算机科学,2013,0(4):295-297

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!