[Numpy-discussion] Neighbour-frequency matrix

Vebjorn Ljosa vebjorn@ljosa....
Wed Jul 15 19:45:59 CDT 2009


On Jul 15, 2009, at 19:37, David Warde-Farley wrote:
>
> Just curious - I noticed in the comments that you (or someone) said
> there's a problem in the original paper's definition. Do you have any
> idea which feature that concerned?

The comments in our previous (Matlab) version of CellProfiler [1]  
claims that it's H7 (sum of variance).  Unfortunately I don't have any  
more details than that.

Vebjorn

[1] https://svnrepos.broad.mit.edu/CellProfiler/trunk/CellProfiler/Modules/MeasureTexture.m



More information about the NumPy-Discussion mailing list