Color Transfer to greyscale images using texture spectrum

Ye Ji, Hong Bo Liu, Xiu Kun Wang, Yi Yuan Tang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Scopus citations

Abstract

Color Transfer between two images is one of the most common tasks in image processing. In this paper, we present a method of pattern recognition to increase the successful possibility of transferring color from color image to grayscale image. A kind of texture descriptor, texture spectrum, plays an important role in the whole procedure. Source image retrieval is used and based on texture-spectrum similarity, which can find the most suitable color images in a color image database. Further more, texture-spectrum is also considered to sample color pixels reasonably. We found that the method works well and it can be successfully applied to a variety of images.

Original languageEnglish (US)
Title of host publicationProceedings of 2004 International Conference on Machine Learning and Cybernetics
Pages4057-4061
Number of pages5
StatePublished - 2004
Externally publishedYes
EventProceedings of 2004 International Conference on Machine Learning and Cybernetics - Shanghai, China
Duration: Aug 26 2004Aug 29 2004

Publication series

NameProceedings of 2004 International Conference on Machine Learning and Cybernetics
Volume7

Other

OtherProceedings of 2004 International Conference on Machine Learning and Cybernetics
Country/TerritoryChina
CityShanghai
Period8/26/048/29/04

Keywords

  • Color Transfer
  • Content-based Image Retrieval
  • Pattern recognition
  • Texture Spectrum

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Color Transfer to greyscale images using texture spectrum'. Together they form a unique fingerprint.

Cite this