Similarity based image in painting method

Nie Dongdong*, Ma Lizhuang, Xiao Shuangjiu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

A similarity based image inpainting method is introduced in this paper, which can be used to automatically fill the regions needing to he erased by using the surrounding information in the image. The method is boxed on analyzing the previous image inpainting methods, especially improving the method proposed hy Criminisi et al. In nur method, a more robust method is adopted to compute the filling order, which overcome the problem arising when the image gradients of some pixels on the source region contour are just zeros. And a new mapping term is proposed in computing the matching cost to penalize the source regions repeatedly sampled, which practically avoid the artificial repetition problem in the inpainted results.

Original languageEnglish
Title of host publicationMMM2006
Subtitle of host publication12th International Multi-Media Modelling Conference - Proceedings
Pages344-347
Number of pages4
StatePublished - 2006
Externally publishedYes
EventMMM2006: 12th International Multi-Media Modelling Conference - Beijing, China
Duration: 4 Jan 20066 Jan 2006

Publication series

NameMMM2006: 12th International Multi-Media Modelling Conference - Proceedings
Volume2006

Conference

ConferenceMMM2006: 12th International Multi-Media Modelling Conference
Country/TerritoryChina
CityBeijing
Period4/01/066/01/06

Fingerprint

Dive into the research topics of 'Similarity based image in painting method'. Together they form a unique fingerprint.

Cite this