hsneto / color_transfer

Super fast color transfer between images

Color Transfer

Getting Started

The color_transfer.hpp header file is an OpenCV implementation based on Color Transfer between Images [Reinhard et al., 2001] and Adrian Rosebrock repository (for Python). The algorithm requires only the mean and standard deviation of pixel intensities for each channel in the Lab* color space.

This is an C++ approach from the above methods, for more information I recommend the above article or Adrian's post on his blog.

Requirements

• OpenCV
• boost/program_options*

*Optional - Used to get the input images from terminal

Installing

Just download this repository and use the header file color_transfer.hpp contained in the color_transfer folder.

Running the tests

A example is in sample folder. After compiling it, run the code below

$ ./color_transfer -s ../images/sunset.jpg -t ../images/ocean_day.jpg

$ ./color_transfer -s ../images/autumn.jpg -t ../images/woods.jpg

$ ./color_transfer -s ../images/old_pic.jpg -t ../images/city.jpg

$ ./color_transfer -s ../images/florest_day.jpg -t ../images/florest_dark.jpg

With docker

xhost +local:docker
XSOCK=/tmp/.X11-unix
XAUTH=/tmp/.docker.xauth
xauth nlist $DISPLAY | sed -e 's/^..../ffff/' | xauth -f $XAUTH nmerge -

docker container run --rm -ti \
-e DISPLAY=$DISPLAY \
-v $XSOCK:$XSOCK \
-v $XAUTH:$XAUTH \
-e XAUTHORITY=$XAUTH \
-v /home/${USER}/${FOLDER}/:/lab/images/ 
hsneto/color_transfer ./transfer -s images/${src_image} -t images/${tgt_image} -p images/${output_image}

xhost -local:docker

Authors

• Humberto da Silva Neto - Initial work

License

MIT LICENSE

Acknowledgments

• Adrian Rosebrock
• [Reinhard et al., 2001]