Earticle

초록

영어

The traditional image completion algorithms based on patches, are to iteratively search the most similar patches in the known region of the whole image to fill the target region. Generally, it is difficult to use these algorithms in practice, due to the big computation. To overcome this problem, in this paper we propose a novel image completion algorithm based on partial regions. Firstly we adapt a randomized correspondence algorithm to search the pixels in the known region that are similar with the pixels in the border of the target region. Then the regions that include the main structures and Texture can be determined by these pixels, and thus we can limit the search space. Secondly we optimize the method of computing filling priorities that is based confidence factor and edge information. Consequently, the correctness of the order of the repairing patches and the success of structures propagation have been enhanced. Finally we improve the method of calculating the most similar patches. A variety of experiments show that, in general, our method yields better results and is 5-10 times faster than the state-of-the-art methods.

목차

Abstract
 1. Introduction
 2. Analysis of Traditional Image Completion
 3. Our Algorithm
  3.1. Initialization Partial Region
  3.2. Computing Patch Filling Priorities
  3.3. Searching Most Similar Patch
 4. Experimental Results and Analysis
 5. Conclusions
 Acknowledgements
 References

키워드

저자

• Mang Xiao [ College of Electronic Information and Engineering, Tongji University, Shanghai 201804,China ]
• Guangyao Li [ College of Electronic Information and Engineering, Tongji University, Shanghai 201804,China ]
• Yunlan Tan [ College of Electronic Information and Engineering, Tongji University, Shanghai 201804,China, School of Electronic Information and Engineering, Jinggangshan University, Ji’an, Jiangxi 343009, China ]
• Lei Peng [ College of Electronic Information and Engineering, Tongji University, Shanghai 201804,China ]
• Yangjian Lv [ College of Electronic Information and Engineering, Tongji University, Shanghai 201804,China ]
• Li Xie [ College of Electronic Information and Engineering, Tongji University, Shanghai 201804,China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Signal Processing, Image Processing and Pattern Recognition

• 간기

  격월간

• pISSN

  2005-4254

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605