期刊文献+

利用纹理和边缘特征的Criminisi改进算法 被引量:20

Improved Criminisi algorithm with the texture and edge features
原文传递
导出
摘要 针对Criminisi算法在图像修复过程中易将纹理部分误认为边缘部分,造成修复顺序偏差而影响修复效果的不足,充分利用图像的纹理结构特征和边缘结构特征,引入差别因子,改进优先权模型,以增强对结构部分的辨别能力,并通过采用新型的搜索方式来克服在修复过程中易产生瑕疵点的不足来完善修复效果。实验结果表明,改进算法较好地克服了原算法所存在的纹理延伸等不足,保持了修复内容的线性结构,其峰值信噪比相比于原算法提高了2~3 dB,具有更好的视觉效果。 In the image inpainting process, the Criminisi algorithm easily confuses texture parts for edge parts, resulting in inpainting sequence deviation which finally influences the inpaint effect. By making full use of the characteristics of image textures and edges, we introduce a differential-factor to improve the ability of the algorithm to distinguish edge parts. At the same time, the improved algorithm uses a new search method to prevent the appearance of flaws during the image inpainting process. Experiments confirm that the improved algorithm can overcome the insufficiencies of the original algorithm such as texture extension and can better maintain linear structures. The Power Signal-to-Noise Ratio of the result compared to the original algorithm has been improved about 2 dB to 3 dB, and the results have a better visual appearance.
出处 《中国图象图形学报》 CSCD 北大核心 2012年第9期1085-1091,共7页 Journal of Image and Graphics
关键词 图像修复 差别因子 优先权模型 线性结构 image inpainting differential-factor priority model linear structure
  • 相关文献

参考文献10

二级参考文献32

  • 1薛峰,张佑生,江巨浪,胡敏.一种快速、有效的纹理合成方法[J].合肥工业大学学报(自然科学版),2005,28(11):1361-1364. 被引量:6
  • 2聂栋栋,Ma Lizhuang,Xiao Shuangjiu.Digital image inpainting by example-based image synthesis method[J].High Technology Letters,2006,12(3):276-282. 被引量:1
  • 3BALLESTER C, BERTALMIO M, CASELLES V, et al. Filling-in by joint interpolation of vector fields and gray levels [ J ]. IEEE Trans on Image Processing, 2001, 10(8): 1200-1211. 被引量:1
  • 4BERTALMIO M, SAPIRO G, CASELLES V, et al. Image inpainting [ C ]/! Proc of the 27th Annual Conference on Computer Graphics and Interactive Techniques. New Orleans: [ s. n], 2000: 417-424. 被引量:1
  • 5CHAN T F, SHEN Jian-hong, ZHOU Hao-min. Total variation wavelet inpaln/ing[ J]. Journal of Mathematical Imaging and Vision, 2006, 25(1) : 107-125. 被引量:1
  • 6CHANT F, KANG H S, SHEN Jian-hong. Euler' s elastica and curvature based inpaintings[ J]. SIAM Joumal on Applied Mathematics, 2002, 63(2) : 564-592. 被引量:1
  • 7LIANG Lin, LIU Ce, XU Ying-qing, et al. Real-time texture synthesis by patch-based sampling[ J]. ACM Trans on Graphics, 2001, 20(3) : 127-150. 被引量:1
  • 8DRORI I, COHEN-OR D, YESHURUN H. Fragment based image completion[ J ]. ACM Trans on Graphics, 2003, 22 ( 3 ) : 303- 312. 被引量:1
  • 9CRIMINISI A, PE' REZ P, TOYAMA K. Object removal by exemplar-based inpainting[ C]// Proc of IEEE Conference on Computer Vision and Pattern Recognition. Madison: [ s. n], 2003: 721-728. 被引量:1
  • 10CRIMINISI A, PE'REZ P, TOYAMA K. Region filling and 6bject removal by exemplar-based image inpainting [ J]. IEEE Trans On Image Processing, 2004, 13(9) : 1200-1212. 被引量:1

共引文献36

同被引文献163

  • 1屈磊,韦穗,梁栋,王年.快速自适应模板图像修复算法[J].中国图象图形学报,2008,13(1):24-28. 被引量:13
  • 2赵岩,汪敬媛,陈贺新,刘静,王珂玮.基于深度图像和半像素的虚拟视点绘制[J].吉林大学学报(工学版),2013,43(S1):256-259. 被引量:4
  • 3吴亚东,张红英,吴斌.数字图像修复技术[M].北京:科学出版社,2010. 被引量:16
  • 4张红英,彭启琮.数字图像修复技术综述[J].中国图象图形学报,2007,12(1):1-10. 被引量:159
  • 5Bertalmio M, Sapiro G, Caselles V, et al. Image inpainting [ A]. In: Processdings of International Conference on Computer Graphics and Interactive Techniques [ C]. New Orleans, Louisiana, USA, 2000: 417-424. 被引量:1
  • 6Chart T F, Shen J H. Non- texture inpainting by curvature - driven diffusions (CDD) [J]. Journal of Visual Communication and Im- age Repr~c~entation. 2001, 12 (4): 436-449. 被引量:1
  • 7Tai X, Borok S, et al. Image denoising using TV - stokes equation with an orientation - matching minimization [ A]. International Con- ference on Scale Space and Variational Methods in Computer Vision [ C]. Voss, Norway, 2009: 90- 501. 被引量:1
  • 8Criminisi A, P6rez P, et al. Region filling and object removal by exemplar- based image inpainting [J]. IEEE Transactions on Image Processing, 2004, 13 (9) : 1200- 1212. 被引量:1
  • 9Martinez- Nofiega R, Roumy A, et al. Exemplar- based image inpainting: fast priority and coherent Nearest Neighbor search [ C]. 2012 INTERNATIONAL WORKSHOP ON MACHINE I.EARNING FOR SIGNAL PRIG, Santander, SPAIN, 2012: 1 - 6. 被引量:1
  • 10Chan T F,Shen J H.Non texture inpainting by Curvature- Driven Diffusions(CDD)[J].J Visual Comm Image Rep, 2001,12(4) :436-449. 被引量:1

引证文献20

二级引证文献110

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