One of the failings of the previous model was that it didn’t encode texture, reviewing the stratigraphic units that we have in the map we can see that most of these units are encoded by both colour and texture. With this knowledge in hand we will try and create a model that uses a window rather than the single pixel that we’ve used in part 1. If you’ve not downloaded the data used in the first article please start there, if you have then we can begin by loading the data and viewing the stratigraphic units.

Hi All, After a while between posts I thought it would be interesting to talk about image classification and its application to scanned geological maps. GSWA has many many 1:250K and 1:100K maps where the only digital version is a scanned print, which depending on your use case might be ok but for machine learning and targeting leave a little to be desired. So let’s discuss a few methods of converting these scanned maps into vector datasets or at least a sensible raster representation.