期刊文献+

一种结合结构和纹理特征修复敦煌壁画的方法 被引量:2

Dunhuang Murals Inpainting with Integrating Structure and Texture Features
下载PDF
导出
摘要 敦煌莫高窟艺术是集建筑、彩塑、壁画于一体的艺术.对莫高窟壁画要科学的、合理的保护和修复.文章根据敦煌壁画内容的特征,用户可以选择相应的纹理因子和结构因子权重,并通过优先度函数来确定填充顺序.在选取与待填充块最相似的匹配块时,以两者之间颜色差别的纹理合成算法为原形,充分考虑了结构的差别,提出了同时以颜色和梯度作为衡量两者之间的相似性量度的纹理合成算法.实验结果表明,对有刮痕和大的剥落块等破损区域的壁画,该方法都有很好的修复效果,并且保留了壁画原有的艺术风格. According to the feature of murals contents, the users can select related texture term and structure term weight, and the filling order is determined through computing patch priorities. To select a patch which is most similar to the patch to be filled is considered texture synthesis algorithm as the primary form based on the difference of color, and the difference between the structures. The experimental results showed that parts of murals with scratches and large flaking patch can he inpainting effectively with the method, and retain murals original artistic style.
作者 黄伟 王书文
出处 《西北民族大学学报(自然科学版)》 2009年第1期60-63,69,共5页 Journal of Northwest Minzu University(Natural Science)
基金 国家自然科学基金项目(No.60675059)
关键词 图像修复 结构 纹理 梯度 image inpainting structure texture gradient
  • 相关文献

参考文献8

  • 1M. Bertalmio, G. Spairo and V. Caselles et al. Image Inpnainting[ C]. Proe. ACM Conf. ComP. Graphics(SIGGRAPH2000), 2000:417 - 424.
  • 2T. Chart and J. Shen. Mathematical models/or local deterministic inpaintings[R]. Submitted. UCLA CAM Report 00 - 11, March, 2000.
  • 3T. Chan and J. Shen. Non- Texture Inpainting by Curvation- Driven Diffusions (CDD)[R]. UCLA CAM TR 00 - 35, September, 2000.
  • 4J.S. de Bonet. Multiresolution sampling procedure for analysis and synthesis of texture images[ C]. In Proc. ACM Conf. Comp. Graphics (SIGGRAPH), volume 31, pages 361 - 368, 1997.
  • 5A. Efros and T. Leung. Texture synthesis by non - parametric sampling[C]. In Proc. Int. Conf. Computer Vision, pages 1033 -- 1038, Kerkyra, Greece, September 1999.
  • 6M. Bertalmio, L. Vese, G. Sapiro and S. Osher. Simultaneous structure and texture image inpainting[J]. IEEE Transactions on Image Processing, 2003,12(8 ) :882- 889.
  • 7Efros A A, Freeman W T. Image quilting for texture synthesis and transfer[ C]. In: Proeeedings of SIGGRAPH 2001, 341 - 346. ISBN 1 - 58113 -292- 1,2001.
  • 8A. Criminisi, P. Perez and K. Toyama. Region Filling and Object Removal by Exemplar- Based Image Inpainting[J]. IEEE Trans. Image Processing, vol. 13, no. 9, pp. 1200 - 1212, Sept, 2004.

同被引文献16

  • 1仵冀颖,阮秋琦,安高云.偏微分方程约束下基于动态大小模块的图像修复模型[J].计算机辅助设计与图形学学报,2007,19(8):1034-1040. 被引量:3
  • 2Bwetalmio M,Spairo G,Caselles V,Ballester C. Image Inpainting[A].New York:acm Press,2000.417-424.
  • 3Criminisi A,Perez P,Toyarna K. Region filling and object removal by exemplar-based image inpainting[J].IEEE Transactions on Image Processing,2004,(09):1200-1212.
  • 4P.F.Felzemszwalb,D.P.Huttenlocher. Efficient graph based image segmentation[J].Int J ComputerVision,2004,(02):167-181.
  • 5J.Lee,R.-H.Park. Adaptive exemplar-based inpainting algorithm using region segmentation[A].Gyeongju,Korea,2011.503-506.
  • 6BERTALMIO M, SAPIRO G. CASELLES V, et al. Image inpaint- ing[ C]// Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques. New York: ACM Press, 2000:417 - 424.
  • 7CHAN T, SHEN F. Mathematical models for local non-texture in- paintings[ J]. SIAM Journal on Applied Mathematics, 2002, 62(3) : 1017 - 1046.
  • 8CHAN T, SHEN J. Non-texture inpainting by curvature-driven dif- fusions[ J]. Journal of Visual Communication and Image Representa- tion, 2001, 12(4): 436-449.
  • 9CRIMINIS1 A, PEREZ P, TOYAMA K. Object removal by exem- plar-based inpainting[ C] // Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2003:721-729.
  • 10JIA Y, LIU P, NIU S. Remove meat image' s reflective areas with a level set constraint inpainting algorithm based on exemplar patch [ C]// Proceedings of the 2011 2nd International Conference on Artificial Intelligence. Management Science and Electronic Com- merce. Washington, DC: IEEE Computer Society, 2011 : 4150 - 4154.

引证文献2

二级引证文献1

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