Paper Title:
Image Completion Using Randomized Correspondence
  Abstract

Image completion techniques can be used to repair unknown image regions. However, existing techniques are too slow for real-time applications. In this paper, an image completion technique based on randomized correspondence is presented to accelerate the completing process. Some good patch matches are found via random sampling and propagated to surrounding areas. Approximate nearest neighbor matches between image patches can be found in real-time. For images with strong structure, straight lines or curves across unknown regions can be manually specified to preserve the important structures. In such case, search is only performed on specified lines or curves. Finally, the remaining unknown regions can be filled using randomized correspondence with structural constraint. The experiments show that the quality and speed of presented technique are much better than that of existing methods.

  Info
Periodical
Advanced Materials Research (Volumes 271-273)
Edited by
Junqiao Xiong
Pages
229-234
DOI
10.4028/www.scientific.net/AMR.271-273.229
Citation
Y. Ling, H. T. Sun, J. W. Han, X. Wang, "Image Completion Using Randomized Correspondence", Advanced Materials Research, Vols. 271-273, pp. 229-234, 2011
Online since
July 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Ma Hua Wang
Session 2: Biomaterial Science
Abstract:For the sake of overcoming the shortage of transitional region and marginal area information loss, especially lost texture information...
492
Authors: Zhong Liang Pan, Ling Chen, Guang Zhao Zhang
III. Display Technologies
Abstract:The defects of LED wafer may be caused from the manufacturing environments such as contamination. The appearance of the defects can results...
251
Authors: Chao Chen, Guo Dong Zhang, Rui Yang, Peng Fei Huo
Chapter 10: Environmentally Sustainable Manufacturing Processes and Systems
Abstract:A medical image registration algorithm based on Renyi generalized mutual information entropy information function and particle swarm -...
3244
Authors: Da Wang, Hong Yu Bian
Chapter 1: Mechatronics
Abstract:In order to further improve the accuracy of the sonar image registration, a novel hybrid algorithm was proposed. It proposed the normalized...
1811
Authors: You E Cheng
Chapter 17: Signal and Intelligent Information Processing
Abstract:A maximization of mutual information based image registration method is described. Firstly Due to the inferiority of image registration using...
2199