Earticle

초록

영어

Image completion is aim to fill the missing regions in images. A robust completion technique using similarity analysis and transformation is proposed to address this problem. Firstly, in order to decrease the search space of patches, random mapping method is used to analyze texture regions which have similar structure and texture with damaged regions. Secondly, geometric and photometric transformations of image are adopted to find the best patches. Thirdly, increasing the accuracy of the structure propagation, a priority calculation method is optimized based on confidence factor and edge information. Finally, a number of examples on real and synthetic images show the effectiveness of our algorithm for image completion.

목차

Abstract
 1. Introduction
 2. Prerequisite Knowledge of Image Completion
 3. Our Algorithm
  3.1. Similarity Analysis
  3.2. Transformation
  3.3. Patch Priorities
  3.4. Searching Best Match-patch
 4. Experimental Results and Analysis
 5. Conclusions
 Acknowledgements
 References

키워드

저자

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

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Multimedia and Ubiquitous Engineering

• 간기

  월간

• pISSN

  1975-0080

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605