Qgis Plugin for automatic extraction of forest from Historical Map, especially for general staff maps (Carte de l'Etat-Major in French)

Made By Nicolas Karasiak and Antoine Lomellini.

Based on the work of Pierre-Alexis Herrault, with the help of Mathieu Fauvel.

If you want a tutorial or some help using this plugin, please consult our wiki.

On Linux simply open terminal and type : pip install scikit-learn

On Windows, you have few more steps to do. Open Windows menu, and search for OsGeo4W Shell, open it as administrator (left click > open as an administrator), then type :
curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py

After get-pip.py has been downloaded write :
python get-pip.py

Now use pip in OsGeo Shell like on Linux. Just type :
pip install scikit-learn

You can now use Random Forest, SVM, or KNN !

If you just need some data samples, you can download them from our samples branch.
To go further you could have a look at our documentation (generated by doxygen).

Herrault, P.-A., Sheeren, D., Fauvel, M., Monteil M., & Paegelow, M. Automatic extraction of forests from historical maps based on unsupervised classification in the CIELab color space. 16th AGILE Conference on Geographic Information Science, Lecture Notes in Geographic Information at the Heart of the Europe, pp 95-112, Springer series. http://link.springer.com/chapter/10.1007%2F978-3-319-00615-4_6#page-1

Herrault, P.-A., Sheeren, D., Fauvel, M., & Paegelow, M. (2015). Vectorisation automatique des forêts dans les minutes de la carte d’état-major du 19 e siècle. Revue Internationale Géomatique, 25(1), 35–51. http://doi.org/10.3166/rig.25.35-51

Herrault, P.-A.. (2015). Extraction de fragments forestiers et caractérisation de leurs évolutions spatio-temporelles pour évaluer l'effet de l'histoire sur la biodiversité: une approche multi-sources. Géographie et aménagement. Laboratoire GEODE UMR 5602 CNRS / Laboratoire DYNAFOR UMR 1201 INRA : Université Toulouse - Jean Jaurès, 410p.