Hi all,

the preliminary code is ready, but it could be improved a lot. For instance, there's a function named maxsigma() which has a lot of nested for loops.

Here is the code:

https://gist.github.com/alexandrejaguar/fd767149b3a667f8be125734893f020d
Could you give me a hand to improve that?

Thank you very much!

Kind regards,

Alex

Em domingo, 8 de maio de 2016 17:20:31 UTC+2, Alexandre Fioravante de Siqueira escreveu:

Hi Josh,

OK, I'm on it. I'll try to implement from the paper.

Alex

Em quarta-feira, 4 de maio de 2016 01:34:38 UTC+2, Josh Warner escreveu:

We do have Otsu, and I think it would be within the scope of scikit-image. 

I think I'd find use for this, personally, and depending on the implementation you may be able to reuse code from simple binary Otsu internally.

Seems reasonable - PR would be welcome!

Josh

On Tuesday, May 3, 2016 at 10:47:00 AM UTC-5, Alexandre Fioravante de Siqueira wrote:

Hi everyone,

I was thinking about using multi-Otsu thresholding for some research. I am used to use the ImageJ available plugin, http://imagej.net/Multi_Otsu_Threshold.

Could you give me a hand on writing such a function which could do this for python? Maybe putting it into scikit-image. Or else, could you point me a better alternative?

Thank you very much!

Alex