期刊文献+

基于Navier-Stokes方程的图像修复算法 被引量:5

A New Algorithm for Image Inpainting Based on the Navier-Stokes Equation
在线阅读 下载PDF
导出
摘要 图像修复是一个基于周围未被损坏信息对图像中丢失或损坏信息进行修补的过程。提出了一个基于Navier-Stokes方程的新的图像修复算法。该算法能够同时在修复区域内部进行信息的填充,而在修复区域外部去除噪声(如果存在)。实验结果表明模型对于图像中划痕,信息丢失,甚至移除整个景物都是有效的。 Image inpainting is the process of filling in missing parts of damaged images based on information gleaned from surrounding areas.A new algorithm for inpainting based on the Navier-Stokes equation,which allows for inpainting inside of the inpainting region and denoising outside of the inpainting region,is outlined.The experimental results show the effective performance of the proposed model in restoring scratched photos,missing parts and even removal of entire objects from images.
出处 《中山大学学报(自然科学版)》 CAS CSCD 北大核心 2012年第1期9-13,18,共6页 Acta Scientiarum Naturalium Universitatis Sunyatseni
基金 国家自然科学基金资助项目(10971234) 国家自然科学基金天元基金资助项目(11026227) 中央高校基本科研业务费专项基金资助项目(10lgzd09) 广州市科技计划资助项目(2010C6-I00011)
关键词 图像修复 图像去噪 NAVIER-STOKES方程 等照度线方向 inpainting denoising Navier-Stokes equation isophote direction
  • 相关文献

参考文献24

  • 1BERTALMIO M, SAPIRO G BALLESTER C, et al. linage inpainting[ C ]//Siggraph 2000, Computer Graphics proceedings, K. Akeley, Ed ACM Press/ ACM SIGGRAPH/ Addison Wesley Longman, 2000:417 - 424.
  • 2BALLESTER C, BERTALMIO M, CASEI,LES V. Filling in by joint interpolation of vector fields and gray levels [ J ]. IEEE Trans Image Processing, 2001, 10 ( 8 ) : 1200 - 1211.
  • 3BERTALMIO M, BERTOZZI A L, SAPIRO G. Navier- Stokes, fluid dynamics and image and video inpainting [ J ]. IEEE Compuler Vision and Pattern Recognition (CVPR), 2001,1: 355-362.
  • 4WILSON A, RYO T. Inpainting with the Navier-Stokes equations [ R]. http://www, math. ucla. edu/- rrtakei/ gradProj/930project, pdf.
  • 5TAI X C, OSHER S, HOLM R. Image inpainting using TV-Stokes equation [ C ] // linage Processing Based on Partial Differential Equations, Springer, Heidelberg, 2006 : 3 - 22.
  • 6CHANT F, SHEN J. Mathematical models for local nontexture inpaintings [ J ]. SIAM J Appl Math, 2002, 62 (3) : 1019 - 1043.
  • 7RUDIN L, OSHER S,FATEMI E. Nonlinear total variation based noise removal algorithms [ J ]. Physica 1), 1992, 60:259 - 268.
  • 8CHANT F, KANG S H, SHEN J. Euler's elastica and curvature-based inpainting [ J]. SIAM J Appl Math, 2002, 63 (2) : 564 - 592.
  • 9CHAN T F, SHEN J, VESE L. Variational PDE models in image processing[ J ]. Notices Am Math Soc, 2003, 50(1): 14-26.
  • 10CHAN T, SHEN J. Non-texture inpainting by curvaturedriven diffusions (CDD) [ J ]. J Visual Comm. Image Rep, 2001, 12(4) :436 -449.

同被引文献46

  • 1杨朝霞,逯峰,田芊芊.自适应双正则参数法在图像恢复中的应用[J].中山大学学报(自然科学版),2005,44(4):20-23. 被引量:5
  • 2马承杰.地震数据访问技术研究[J].石油工业计算机应用,2005,13(4):5-7. 被引量:8
  • 3TIKHONOV A N, ARSENIN V Y. Solutions of ill-posed problems [ M ]. Washington DC: Winston and Sons, 1977.
  • 4RUDIN L, OSHER S, FATEMI E. Nonlinear total varia- tion based noise removal algorithms [ J ]. Physica D, 1992, 60(1/2/3/4): 259-268.
  • 5CHAMBOLLE A. An algorithm for total variation minimi- zation and applications [J]. Journal of Mathematical Im- aging and Vision, 2004, 20(1) : 89 -97.
  • 6BECK A, TEBOULLE M. Fast gradient-based algorithms for constrained total variation image denoising and deblur- ring problems [ J ]. IEEE Transactions on Image Process- ing, 2009, 18(11) : 2419 -2434.
  • 7WEN Y W, CHAN R H. Parameter selection for total variation based image restoration using discrepancy princi- ple [ J ]. IEEE Transactions on Image Processing, 2012, 21(4) : 1770 -1781.
  • 8CHO T S, ZITNICK C L, JOSHI N, et al. Image restora- tion by matching gradient distributions [ J ]. IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 2012, 34(4) : 683 -694.
  • 9ALLARD W K. Total variation regularization for image denoising II, examples [ J]. SIAM J. Imaging Sciences, 2008, 1(4) : 400-417.
  • 10ALLARD W K. Total variation regularization for image denoising III, examples [ J]. SIAM J. Imaging Sciences, 2009, 2 (2) : 532 - 568.

引证文献5

二级引证文献4

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