Adaptive digital image inpainting

Timothy K. Shih, Rong Chi Chang, Liang Chen Lu, Wen Chieh Ko, Chun Chia Wang

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

26 Scopus citations

Abstract

Digital image inpainting is a technique that can repair a portion of damaged or removed image by means of automatic mechanisms. Image inpainting tools can be applied to repairing damaged historical documents. In this paper, we propose an adaptive mechanism, which is based on a color interpolation mechanism. The repairing procedure checks the surrounding information of a damaged pixel and decides the range of references that can be used to compute an interpolated color. We have tested on more than 2000 images include painting, photo, and cartoon drawing. The evaluation shows that our mechanism produces a very good result.

Original languageEnglish
Title of host publicationProceedings - 18th International Conference on Advanced Information Networking and Applications, AINA 2004 Volume 1 (Regional Papers)
EditorsL. Barolli
Pages71-76
Number of pages6
DOIs
StatePublished - 2004
EventProceedings - 18th International Conference on Advanced Information Networking and Applications, AINA 2004 - Fukuoka, Japan
Duration: 29 Mar 200431 Mar 2004

Publication series

NameProceedings - International Conference on Advanced Information Networking and Application (AINA)
Volume1

Conference

ConferenceProceedings - 18th International Conference on Advanced Information Networking and Applications, AINA 2004
Country/TerritoryJapan
CityFukuoka
Period29/03/0431/03/04

Keywords

  • Adaptive inpainting
  • Digital inpainting
  • Image processing
  • Image restoration

Fingerprint

Dive into the research topics of 'Adaptive digital image inpainting'. Together they form a unique fingerprint.

Cite this