Fabric image recolorization based on intrinsic image decomposition

Chen Xu, Yu Han, George Baciu, Min Li

Research output: Journal article publicationJournal articleAcademic researchpeer-review

4 Citations (Scopus)

Abstract

Fabric image recolorization is widely used in assisting designers to generate new color design proposals for fabric. In this paper, a new image recolorization method is proposed. Different from classical image recolorization methods, which need some complicated interactive operations from users, our proposed method can achieve automatic recolorization of images. The proposed method contains three sequential phases: a phase of extracting representative colors from fabric images; an image segmentation phase; and an image reconstruction phase by using given color themes. Integrated with intrinsic image decomposition, a new image segmentation model is designed in a variational framework, and an algorithm is given to solve the model. Our image recolorization results are images that are reconstructed by the composition of the image segmentation results and the given color themes. Numerical results demonstrate that our newly proposed intrinsic image decomposition-based image recolorization method can generate better results than the classical cartoon-and-texture decomposition-based method.

Original languageEnglish
Pages (from-to)3617-3631
Number of pages15
JournalTextile Reseach Journal
Volume89
Issue number17
DOIs
Publication statusPublished - 1 Sep 2019

Keywords

  • color theme
  • fabric design
  • image segmentation
  • variational model
  • yarn structure

ASJC Scopus subject areas

  • Chemical Engineering (miscellaneous)
  • Polymers and Plastics

Cite this