Metal highlight spots removal based on multi-light-sources and total variation inpainting

  • Yao Li*
  • , Lizhuang Ma
  • *Corresponding author for this work

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

4 Scopus citations

Abstract

We present a novel highlight spots removal algorithm which can remove the highlight spots on the metal surface fast and efficiently. First, multi-light-sources is adopted to reduce the large region of the highlight spots which use several different light sources to get images and use the gradient to reconstruct an image. Multi-light-sources method cannot deal with the overlapped highlight spots. So we use the total variation inpainting model to restore the diffuse region from neighborhood of the specular spots to eliminate highlight spots completely. The light spots on the surface of the metal objects with complex texture can be removed effectively, and the physical property of the surface maintains well. Experiments show that the stereo matching algorithm whose input is the image pair after using the highlight spots removal algorithm can get much better result.

Original languageEnglish
Title of host publicationProceedings - VRCIA 2006
Subtitle of host publicationACM International Conference on Virtual Reality Continuum and its Applications
Pages323-326
Number of pages4
DOIs
StatePublished - 2006
Externally publishedYes
EventACM International Conference on Virtual Reality Continuum and its Applications, VRCIA 2006 - Hong Kong, China
Duration: 14 Jun 200617 Jun 2006

Publication series

NameProceedings - VRCIA 2006: ACM International Conference on Virtual Reality Continuum and its Applications

Conference

ConferenceACM International Conference on Virtual Reality Continuum and its Applications, VRCIA 2006
Country/TerritoryChina
CityHong Kong
Period14/06/0617/06/06

Keywords

  • Highlight spot removal
  • Inpainting
  • Metal surface
  • Multi-light-source

Fingerprint

Dive into the research topics of 'Metal highlight spots removal based on multi-light-sources and total variation inpainting'. Together they form a unique fingerprint.

Cite this