Skip to content

Image region description using orthogonal combination of local binary patterns enhanced with color information

License

Notifications You must be signed in to change notification settings

ECL-LIRIS/OC-LBP

Repository files navigation

---------------------------------------------------------------------------

AUTHOR

Chao Zhu

---------------------------------------------------------------------------

CONTACT

email : [email protected]

---------------------------------------------------------------------------

LICENCE

Source code is available under the GNU General Public License. In short, if
you distribute a software that uses OC-LBP, you have to distribute it under
GPL with the source code.

For a copy of the GPL: https://www.gnu.org/copyleft/gpl.html

---------------------------------------------------------------------------

REFERENCE

If you use the code of OC-LBP in your research, please give a reference to:

C. Zhu, C.-E. Bichot and L. Chen, Image region description using orthogonal
combination of local binary patterns enhanced with color information,
Pattern Recognition (2013), https://dx.doi.org/10.1016/j.patcog.2013.01.003

---------------------------------------------------------------------------

USAGE

1. Compile the mex_computeLBPonKeypoints.cpp file if necessary (the pre-
   compiled versions for 64-bit Linux and 32/64-bit Windows are provided,
   and usually they will work):
   
   >> mex mex_computeLBPonKeypoints.cpp


2. Run extract_OCLBP_descriptor.m to compute gray/color OC-LBP descriptor
   (see the M-file for more detailed instruction of each input arguments):
   
   >> load 000019_kps.mat
   >> descs = extract_OCLBP_descriptor('000019.jpg',kps,8,1,'gray')

---------------------------------------------------------------------------

ACKNOWLEDGMENT

Great thanks to Machine Vision Group, University of Oulu for sharing their
code of LBP, which is used in the OC-LBP function.

---------------------------------------------------------------------------

About

Image region description using orthogonal combination of local binary patterns enhanced with color information

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published