1

I'm trying to figure out how to classify a group of rasters. These can't be joined as they have overlaps which must be kept. I was wondering whether there's a way of obtaining grouped statistics - eg histograms - which might help me visually classify either groups, or all of the data.

Basically, an efficient way to classify them all based on aggregate data. I think I'll probably be able to add symbology to more than one once I have the class limits established.

They're all separate ADF files at the moment - I'm wondering whether I should get these into a geodatabase first, somehow.

Improve this question

1 Answer 1

Reset to default
1

After histogram equalization you can use Maximum Likelihood Classification - this tool considers both the variances and covariances of the class signatures when assigning each cell to one of the classes represented in the signature file. With the assumption that the distribution of a class sample is normal, a class can be characterized by the mean vector and the covariance matrix. Given these two characteristics for each cell value, the statistical probability is computed for each class to determine the membership of the cells to the class. When the default EQUAL A priori probability weighting option is specified, each cell is assigned to the class to which it has the highest probability of being a member.

Improve this answer
4
  • Don't I need to mosaic values in order to do the Maximum Likelihood Classification? Is it in any way similar to Natural Breaks? Sorry - my knowledge is pretty basic.
    – Joules
    Sep 8, 2013 at 10:55
  • at mosaic tool there are options to colormap match this will take all the color maps into consideration when mosaicking. If all possible values are already used (for the bit depth), it will attempt to match the value with the closest color that is available.
    – Dror Har Gil
    Sep 8, 2013 at 11:10
  • This is difficult as I'm dealing with densities of distinct / different classes in each of the rasters - they exist simultaneously so can't be combined in any of those ways. Thanks for your contribution though.
    – Joules
    Sep 8, 2013 at 11:14
  • Histogram Equalization with MATLAB or with the new arcmap tool - Interactive histogram stretch.
    – Dror Har Gil
    Sep 8, 2013 at 11:30

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.