<div dir="ltr"><font size="2" face="arial, sans-serif">Hi all,</font><div><font size="2" face="arial, sans-serif">I am having a bad time trying to correct the first version of this code.</font></div><div><font size="2" face="arial, sans-serif">The values from my function and Tosa's does not match. In my tests, my </font><span style="font-family: arial, sans-serif; font-size: small;">maxSigma is higher than his; I believe I am having a problem with </span><span style="font-family: arial, sans-serif; font-size: small;">the values returned from the histogram.</span></div><div><span style="font-family: arial, sans-serif; font-size: small;">Could you give me a hand on that? This is the code so far:</span></div><div><font size="2" face="arial, sans-serif"><a href="https://github.com/alexandrejaguar/software/blob/master/threshold_multiotsu.py">https://github.com/alexandrejaguar/software/blob/master/threshold_multiotsu.py</a></font></div><div><font size="2" face="arial, sans-serif">Thanks for your time!</font></div><div><font size="2" face="arial, sans-serif">Kind regards,</font></div><div><font size="2" face="arial, sans-serif"><br></font></div><div><font size="2" face="arial, sans-serif">Alex<br></font><br>Em segunda-feira, 9 de maio de 2016 19:06:46 UTC+2, Alexandre Fioravante de Siqueira  escreveu:<blockquote class="gmail_quote" style="margin: 0;margin-left: 0.8ex;border-left: 1px #ccc solid;padding-left: 1ex;"><div dir="ltr">Done (for now): <a href="https://github.com/scikit-image/scikit-image/pull/2076" target="_blank" rel="nofollow" onmousedown="this.href='https://www.google.com/url?q\x3dhttps%3A%2F%2Fgithub.com%2Fscikit-image%2Fscikit-image%2Fpull%2F2076\x26sa\x3dD\x26sntz\x3d1\x26usg\x3dAFQjCNGIfK59ZSA9l5bh26oH9R6XM6z9GQ';return true;" onclick="this.href='https://www.google.com/url?q\x3dhttps%3A%2F%2Fgithub.com%2Fscikit-image%2Fscikit-image%2Fpull%2F2076\x26sa\x3dD\x26sntz\x3d1\x26usg\x3dAFQjCNGIfK59ZSA9l5bh26oH9R6XM6z9GQ';return true;">https://github.com/<wbr>scikit-image/scikit-image/<wbr>pull/2076</a>.<br><br>Em segunda-feira, 9 de maio de 2016 12:14:59 UTC+2, Alexandre Fioravante de Siqueira  escreveu:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Hi all,<div>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.</div><div>Here is the code:</div><div><a href="https://gist.github.com/alexandrejaguar/fd767149b3a667f8be125734893f020d" rel="nofollow" target="_blank" onmousedown="this.href='https://www.google.com/url?q\x3dhttps%3A%2F%2Fgist.github.com%2Falexandrejaguar%2Ffd767149b3a667f8be125734893f020d\x26sa\x3dD\x26sntz\x3d1\x26usg\x3dAFQjCNGo9xHoXpRApdZnp5mbVZronbKzjw';return true;" onclick="this.href='https://www.google.com/url?q\x3dhttps%3A%2F%2Fgist.github.com%2Falexandrejaguar%2Ffd767149b3a667f8be125734893f020d\x26sa\x3dD\x26sntz\x3d1\x26usg\x3dAFQjCNGo9xHoXpRApdZnp5mbVZronbKzjw';return true;">https://gist.github.com/<wbr>alexandrejaguar/<wbr>fd767149b3a667f8be125734893f02<wbr>0d</a><br>Could you give me a hand to improve that?</div><div>Thank you very much!</div><div>Kind regards,</div><div><br></div><div>Alex<br><br>Em domingo, 8 de maio de 2016 17:20:31 UTC+2, Alexandre Fioravante de Siqueira  escreveu:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Hi Josh,<div>OK, I'm on it. I'll try to implement from the paper.</div><div><br></div><div>Alex<br><br>Em quarta-feira, 4 de maio de 2016 01:34:38 UTC+2, Josh Warner  escreveu:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">We do have Otsu, and I think it would be within the scope of scikit-image. <div><br></div><div>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.</div><div><br></div><div>Seems reasonable - PR would be welcome!</div><div><br></div><div>Josh<br><br>On Tuesday, May 3, 2016 at 10:47:00 AM UTC-5, Alexandre Fioravante de Siqueira wrote:<blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div>Hi everyone,</div><div>I was thinking about using multi-Otsu thresholding for some research. I am used to use the ImageJ available plugin, <a href="http://imagej.net/Multi_Otsu_Threshold" rel="nofollow" target="_blank" onmousedown="this.href='http://www.google.com/url?q\x3dhttp%3A%2F%2Fimagej.net%2FMulti_Otsu_Threshold\x26sa\x3dD\x26sntz\x3d1\x26usg\x3dAFQjCNGF-axkgTI91tL1CYXjNFajAPii3A';return true;" onclick="this.href='http://www.google.com/url?q\x3dhttp%3A%2F%2Fimagej.net%2FMulti_Otsu_Threshold\x26sa\x3dD\x26sntz\x3d1\x26usg\x3dAFQjCNGF-axkgTI91tL1CYXjNFajAPii3A';return true;">http://imagej.net/Multi_Otsu_<wbr>Threshold</a>.</div><div>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?</div><div>Thank you very much!</div><div><br></div><div>Alex</div></div></blockquote></div></div></blockquote></div></div></blockquote></div></div></blockquote></div></blockquote></div></div>