Advanced search
1 file | 7.93 MB

Texture and color descriptors as a tool for context-aware patch-based image inpainting

Tijana Ruzic (UGent) and Aleksandra Pizurica (UGent)
Author
Organization
Abstract
State-of-the-art results in image inpainting are obtained with patch-based methods that fill in the missing region patch-by-patch by searching for similar patches in the known region and placing them at corresponding locations. In this paper, we introduce a context-aware patch-based inpainting method, where the context is represented by texture and color features of a block surrounding the patch to be filled in. We use this context to recognize other blocks in the image that have similar features and then we constrain the search for similar patches within them. Such an approach guides the search process towards less ambiguous matching candidates, while also speeding up the algorithm. Experimental results demonstrate benefits of the proposed context-aware approach, both in terms of inpainting quality and computation time.
Keywords
inpainting, patch-based algorithms, Gabor filters, REPRESENTATION, PROPAGATION, SCENE, COMPLETION

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 7.93 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Ruzic, Tijana, and Aleksandra Pizurica. 2012. “Texture and Color Descriptors as a Tool for Context-aware Patch-based Image Inpainting.” In Proceedings of SPIE, ed. KO Egiazarian, SS Agaian, AP Gotchev, J Recker, and G Wang. Vol. 8295. Bellingham, WA, USA: SPIE-INT SOC OPTICAL ENGINEERING.
APA
Ruzic, T., & Pizurica, A. (2012). Texture and color descriptors as a tool for context-aware patch-based image inpainting. In KO Egiazarian, S. Agaian, A. Gotchev, J. Recker, & G. Wang (Eds.), Proceedings of SPIE (Vol. 8295). Presented at the Conference on Image Processing - Algorithms and Systems X and Parallel Processing for Imaging Applications II, Bellingham, WA, USA: SPIE-INT SOC OPTICAL ENGINEERING.
Vancouver
1.
Ruzic T, Pizurica A. Texture and color descriptors as a tool for context-aware patch-based image inpainting. In: Egiazarian K, Agaian S, Gotchev A, Recker J, Wang G, editors. Proceedings of SPIE. Bellingham, WA, USA: SPIE-INT SOC OPTICAL ENGINEERING; 2012.
MLA
Ruzic, Tijana, and Aleksandra Pizurica. “Texture and Color Descriptors as a Tool for Context-aware Patch-based Image Inpainting.” Proceedings of SPIE. Ed. KO Egiazarian et al. Vol. 8295. Bellingham, WA, USA: SPIE-INT SOC OPTICAL ENGINEERING, 2012. Print.
@inproceedings{2121284,
  abstract     = {State-of-the-art results in image inpainting are obtained with patch-based methods that fill in the missing region patch-by-patch by searching for similar patches in the known region and placing them at corresponding locations. In this paper, we introduce a context-aware patch-based inpainting method, where the context is represented by texture and color features of a block surrounding the patch to be filled in. We use this context to recognize other blocks in the image that have similar features and then we constrain the search for similar patches within them. Such an approach guides the search process towards less ambiguous matching candidates, while also speeding up the algorithm. Experimental results demonstrate benefits of the proposed context-aware approach, both in terms of inpainting quality and computation time.},
  articleno    = {82951P},
  author       = {Ruzic, Tijana and Pizurica, Aleksandra},
  booktitle    = {Proceedings of SPIE},
  editor       = {Egiazarian, KO and Agaian, SS and Gotchev, AP and Recker, J and Wang, G},
  issn         = {0277-786X},
  keyword      = {inpainting,patch-based algorithms,Gabor filters,REPRESENTATION,PROPAGATION,SCENE,COMPLETION},
  language     = {eng},
  location     = {Burlingame, CA, USA},
  pages        = {11},
  publisher    = {SPIE-INT SOC OPTICAL ENGINEERING},
  title        = {Texture and color descriptors as a tool for context-aware patch-based image inpainting},
  url          = {http://dx.doi.org/10.1117/12.923098},
  volume       = {8295},
  year         = {2012},
}

Altmetric
View in Altmetric
Web of Science
Times cited: