This repos provides an MATLAB code implementation for the Statistical Approach to Texture Classification from Single Images paper by Varma et. al.
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
LICENSE
README.md
build_histogram_models.m
build_texton_dictionary.m
chi2dist.m
classify_images.m
demo_curet.m
filter_response2histogram.m
fuf.m
getFilterParameters.m
get_image.m
get_texton_map.m
im2filter_response.m
knn_calc_dist.m
makeLMfilters.m
makeRFSfilters.m
makeSfilters.m

README.md

Statistical Approach to Texture Classification from Single Images

This repos provides an implementation for the "Statistical Approach to Texture Classification from Single Images" paper by Varma et. al.

The filters (RFS, LM, S) used in this repos are from this link

It is not documented yet. Since I know that it will take me some time to write the documentation, I decided to provide this initial version of the code. There is a lot of work that can help make this code better. So any contributions will be welcomed.

Libraries

To be able to run this code, you need to download the following libraries

VLFeat Library is used to calculate K-means (vl_kmeans) and the distance between new nodes and pre-computed centroids (vl_alldist). Classification toolbox is used to find the nearest neighbor during the classification phase.

Setup

  1. Download the code.
  2. Download the [Classification toolbox for
  3. MATLAB, by Milano Chemometrics and QSAR Research Group](http://michem.disat.unimib.it/chm/download/softwares/help_classification/web.htm).
  4. Update the knn_calc_dist.m file with the file inside this repos, to support chi-square distance
  5. Update the "rootpath" variable in demo_curet.m to point to Columbia-Utrecht dataset folder on your machine.
  6. Run demo_curet.m to test the performance over Columbia-Utrecht dataset.

I will try to update the documentation incrementally to provide more instructions to make using this code easier.

Contributor list

  1. Ahmed Taha
  2. Aleksandrs Ecins

License

TextureClassification_FilterBank is released under the BSD 2-Clause license. The code is released for unrestricted use.