Skip to content

A Further Enhanced Implementation of the Colour Transfer Method proposed by E Reinhard et al. (Python reimplementation)

License

Notifications You must be signed in to change notification settings

minh-nguyenhoang/Enhanced-Image-Colour-Transfer-2

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

42 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Enhanced Image-Colour-Transfer-2

===========================================================================

Python version can be found in 'enhance2.py '. Original repository can be found in This repository. You can give this and the original repo a start if you find this useful.

===========================================================================

A Further Enhanced Implementation of the Colour Transfer Method proposed by E Reinhard et al.

This repository is supported by a web app, a Medium article and by executable code. See details below.

A further revised version of the standard basic processing method is proposed which utilises image representation in the l-alpha-beta colour space and which supersedes the Enhanced Method described here. As with the basic processing, account is taken of the the mean and standard deviation values of the respective l-alpha-beta components but, in addition, the correlation between the 'alpha' and 'beta' colour components is adddressed. Additional new options allow for the matching of higher moments of the colour components beyond the second moments, for the adjustment of image saturation and for the implementation of flexible image shading options. The processing is described further in the file 'Enhanced Image-Colour-Transfer.pdf' in the 'Documents' sub-folder.

The program 'Main.cpp ' runs under C++ using OpenCV. Processing options may be specified by modifying statements within the 'Processing Selections' section in the main routine.

The following images illustrate the processing describe here.

The first image in each set is the target image and the second is the colour source image. The third image shows the effects of standard basic processing as proposed by E Reinhard et al. The final image has been subject to the further enhanced processing using the default processing options specified in the source code and in its asssociated documentation.

              Target Image                         Palette Image                     Standard Processing              Enhanced Processing

Composite of Vase Image: Inputs and Outputs

Composite of Autumn Image: Inputs and Outputs

Composite of Flowers Image: Inputs and Outputs

A web app implementing these methods is available here.

A Medium article discussing these methods is available here.

An executable for the 'Further Enhanced-Image-Colour-Transfer' processing is available here.

Please star this respository if you find any of these facilities to be commendable.

About

A Further Enhanced Implementation of the Colour Transfer Method proposed by E Reinhard et al. (Python reimplementation)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 67.0%
  • Python 33.0%