期刊文献+

基于分组行进算法的图像修补方法 被引量:1

Digital Image Inpainting Based on Group Marching Method
下载PDF
导出
摘要 图像修补是图像恢复研究中的一个重要内容,它的目的是根据图像的现有信息来自动恢复丢失的信息。虽然图像修补的基本思想十分简单,但是许多的图像修补算法都十分复杂,而且难于实现。快速行进算法(FMM)与水平集法(Level Set)相结合进行曲线进化是一种高效的曲线进化算法,该算法的时间复杂度是O(NlbN)。Kim提出了另一种水平集的曲线进化算法——分组行进算法(GMM),该算法的时间复杂度是O(N)。受其启发,为了更快地进行图像修补,提出了一种基于GMM算法的图像修补的新算法,并研究了对GMM算法的细节改进。为了验证算法的快速性,还给出了使用Bertalmio提出的算法、Telea提出的算法以及新算法对同一幅图片进行修补的实验结果。通过比较发现,该新算法在大幅度提高修补速度的同时,仍能保持较好的修补效果。 Image inpainting is an important research topic in the area of image restoration. Its objective is to restore the lost information according to around image information. Although the inpainting basics are straightforward, most inpainting techniques published in the literature are complex to understand and implement. Fast marching method (FMM) is an efficient algorithm for level set applications whose total computation cost is 0 (NlbN)). Kim presented a more efficient algorithm called group marching method(GMM) with the complexity of O(N). Motivated by his work, we propose a new technique for image inpainting based on GMM. Examples of experiment using Bertalmio's algorithm, Telea's algorithm, and our algorithm are illustrated. The result shows that the technique we proposed is faster than the other inpainting methods while preserving almost the same inpainting result.
出处 《中国图象图形学报》 CSCD 北大核心 2007年第5期799-804,共6页 Journal of Image and Graphics
基金 国家重点基础研究发展"973"计划前期研究专项资助项目(2006CB708305)
关键词 图像复原 图像修补 分组行进算法 快速行进算 image restoration, image inpainting, group marching method( GMM), fast marching method(FMM)
  • 相关文献

参考文献8

  • 1Bertalmio M,Sapiro G,Caselles V,et al.Image inpainting[A].In:Proceedings of SIGGRAPH 2000[C],New York,NY,USA,2000:417 ~424.
  • 2Gomes J,V elho L.Image Processing for Computer Graphics[M].New York:Springer-Verlag,1997.
  • 3许威威,潘志庚,张明敏.一种基于整体变分的图象修补算法[J].中国图象图形学报(A辑),2002,7(4):351-355. 被引量:30
  • 4Sethian J.A fast marching level set method for monotonically advancing fronts[J].Proceedings of the National Academy Science,1996,93(4):1591 ~ 1595.
  • 5Telea A.An Image inpainting technique based on fast marching method[J].Journal of Graphics Tools,2004,9(1):25 ~36.
  • 6Kim S.An O(N) level set method for Eikonal equation[J].SIAM Journal on Scientific Computing,2001,22(6):2178 ~2193.
  • 7Sethian J.A Level Set Methods[M].Cambridge,UK:Cambridge University Press,1996.
  • 8Osher S,Sethian J A.Front propagating with curvature-dependent speed:algorithm based on Hamilton-Jacobi formulation[J].Journal of Computational Physics,1988,79:12 ~49.

二级参考文献2

共引文献29

同被引文献15

  • 1张平,檀结庆,何蕾.基于离散小波变换的图像修补方法[J].计算机应用研究,2007,24(9):287-289. 被引量:9
  • 2Bertalmio M, Sapiro G, Caselles V, et al. Image inpainting[ C ]//Proceedings of the 27th Annual Conference on Computer Graphics and Inter- active Techniques. NewYork, USA : ACM Press/Addison-Wesley Publishing Co. , 2000 : 417 - 424.
  • 3Chan T F, Shen J. Nontexture inpainting by curvature-driven diffusions [ J ]. Journal of Visual Communication and Image Representation, 2001, 12(4) : 436 -449.
  • 4Shen J, Chan T F. Mathematical models for local nontexture inpaintings[ J]. SIAM Journal on Applied Mathematics, 2002, 62 (3) : 1019 - 1043.
  • 5Chan T F, Kang S H, Shen J. Euler's elastica and curvature-based inpainting[ J]. SIAM Journal on Applied Mathematics, 2002, 62 ( 1 ) : 564 - 592.
  • 6Esedoglu S, Shen J. Digital inpainting based on the Mumford-Shall-Euler image model[ J]. European Journal of Applied Mathematics, 2002, 13(4) : 353 -370.
  • 7Wong A, Orchard J. A nonloeal-means approach to exemplar-based inpainting[ C ]//15th IEEE International Conference on Image Processing. Piseataway, N J, USA: IEEE, 2008 : 2600 - 2603.
  • 8I-Jan Y, Shi P. An adaptive level-selecting wavelet transform for texture defect detection [ J ]. Image and Vision Computing, 2007, 25 (8) :1239 -1248.
  • 9Liu J, Moulin P. Information-theoretic analysis of interscale and intrascale dependencies between image wavelet coefficients [ J ]. IEEE Trans- actions on Image Processing, 2001, 10 (11 ) : 1647 -1658.
  • 10Shih T K, Tang N C, Hwang J N. Exemplar-based video inpainting without ghost shadow artifacts by maintaining temporal continuity [ J ]. IEEE Transactions on Circuits and Systems for Video Technology, 2009, 19(3 ) : 347 -360.

引证文献1

二级引证文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部