[R-sig-Geo] Map digitization and classification

[Michael Sumner]

Hi Tim, wow that looks it could be rather difficult to automate. It's
probably easiest just to visualize them in a map plot and then use
locator() to recreate the locations for each symbol. That would not be
too difficult, but there are a few options.

Is the data not also published in the atlas in tabular form?

If I had to do this myself I'd probably use an interactive GIS like
Manifold, but it certainly could be done in R fairly simply with some
manual handling. The major problem is probably the overall accuracy
when you try to georegister the scans.

Cheers, Mike.

On Sat, Mar 19, 2011 at 11:28 AM, tsippel <tsippel at gmail.com> wrote:
> Here is an example of one of these map sets.  This is the original as it was
> sent to me, but I would crop each map individually.
>
> https://docs.google.com/viewer?a=v&pid=explorer&chrome=true&srcid=0B0d3zfSSPFQsY2MxODEyZWEtZTRkZC00OTk2LTgwY2YtYTZkYzcwZGYxZDll&hl=en&authkey=CLmWvWc
>
> <https://docs.google.com/viewer?a=v&pid=explorer&chrome=true&srcid=0B0d3zfSSPFQsY2MxODEyZWEtZTRkZC00OTk2LTgwY2YtYTZkYzcwZGYxZDll&hl=en&authkey=CLmWvWc>In
> my original post I asked about classifying squares and triangle for the sake
> of simplicity, but as you can see the symbols used for this (published in
> the 1970s) aren't that easy to distinguish.  Luckily, I don't think there is
> too much background noise, but maybe the 10 x10 grid lines will be
> problematic?
>
> Since this was scanned from the pages of a bound book, a curvature was
> induced in the scanned copy too, so the borders aren't perfectly square.  We
> might be able to resolve this by scanning things more carefully, but your
> thoughts on this are very welcome too.
>
> Thanks,
>
> Tim
>
> On Fri, Mar 18, 2011 at 2:04 PM, Barry Rowlingson <
> b.rowlingson at lancaster.ac.uk> wrote:
>
>> On Fri, Mar 18, 2011 at 9:44 PM, tsippel <tsippel at gmail.com> wrote:
>> > I have a series of scanned global maps (from a bound Atlas) of
>> oceanographic
>> > sampling effort that I would like to classify. On 1 x1 lat/lon grids are
>> > symbols that represent sampling density.  I need to read in these scanned
>> > maps, and classify the symbols (squares are classified as 1, triangles as
>> 2,
>> > etc.) and hopefully store them in raster grid files (.asc) for analysis.
>> >
>> > After some trawling through CRAN looking for packages for this, it is not
>> > yet apparent to me which is best.  I've considered using a GIS for this
>> (ie.
>> > GRASS), but I'm not sure if that is a more complicated solution to a
>> simpler
>> > problem.  I need to process a directory of these images, so scripting the
>> > process to loop over the directory would be ideal.
>>
>>  So you've got some high resolution page images and want to do
>> recognition of the shapes in the grid cells?
>>
>>  Depending on how much noise there is it might be easy or difficult...
>> Any chance you can get us a sample image, or a section of one? How
>> many different symbols are there, and how big is the grid? I guess
>> global means 360x180, but what's the image resolution? Is there also a
>> map outline background to confuse things? MIght be easier to attack
>> this with an image processing toolbox like imageJ...
>>
>> Barry
>>
>
>        [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>



-- 
Michael Sumner
Institute for Marine and Antarctic Studies, University of Tasmania
Hobart, Australia
e-mail: mdsumner at gmail.com