bug siox segmentation?
Locked
 
|
hi,
I have problems using the siox plugin. The mask I create and save based on my RGB picture is not the same (result is different) when i apply this mask to this RGB picture. Has anyone an idea or observed similar problems? picture and wrong masks you can find here: https://www.dropbox.com/s/jct64wudgbxxcoc/Fiji%20siox%20bug.pptx?dl=0 https://www.dropbox.com/s/daew3gbhfnpp10m/G23_1_SMA_1_800_250613a.zvi?dl=0 thank you in advance anett -- ImageJ mailing list: http://imagej.nih.gov/ij/list.html |
Re: bug siox segmentation?
|
|
Hello Anett,
Did you select the "Allow multiple foreground components" option in the GUI? This is somehow a bug, because when you applied the saved segmentator it looks for multiple foreground objects even if you didn't want to. ignacio On Wed, Sep 24, 2014 at 12:58 PM, Anett Jannasch < [hidden email]> wrote: > hi, > > I have problems using the siox plugin. The mask I create and save based on > my RGB picture is not the same (result is different) when i apply this mask > to this RGB picture. Has anyone an idea or observed similar problems? > > picture and wrong masks you can find here: > > https://www.dropbox.com/s/jct64wudgbxxcoc/Fiji%20siox%20bug.pptx?dl=0 > https://www.dropbox.com/s/daew3gbhfnpp10m/G23_1_SMA_1_800_250613a.zvi?dl=0 > > thank you in advance > > anett > > -- > ImageJ mailing list: http://imagej.nih.gov/ij/list.html > -- Ignacio Arganda-Carreras, Ph.D. Seung's lab, 46-5065 Department of Brain and Cognitive Sciences Massachusetts Institute of Technology 43 Vassar St. Cambridge, MA 02139 USA Phone: (001) 617-324-3747 Website: http://bioweb.cnb.csic.es/~iarganda/index_EN.html -- ImageJ mailing list: http://imagej.nih.gov/ij/list.html |
Re: bug siox segmentation?
|
|
Please, update Fiji, I just released a version that fix the bug.
Cheers! ignacio On Wed, Sep 24, 2014 at 2:18 PM, Ignacio Arganda-Carreras < [hidden email]> wrote: > Hello Anett, > > Did you select the "Allow multiple foreground components" option in the > GUI? > > This is somehow a bug, because when you applied the saved segmentator it > looks for multiple foreground objects even if you didn't want to. > > ignacio > > On Wed, Sep 24, 2014 at 12:58 PM, Anett Jannasch < > [hidden email]> wrote: > >> hi, >> >> I have problems using the siox plugin. The mask I create and save based >> on my RGB picture is not the same (result is different) when i apply this >> mask to this RGB picture. Has anyone an idea or observed similar problems? >> >> picture and wrong masks you can find here: >> >> https://www.dropbox.com/s/jct64wudgbxxcoc/Fiji%20siox%20bug.pptx?dl=0 >> https://www.dropbox.com/s/daew3gbhfnpp10m/G23_1_SMA_1_800_250613a.zvi?dl=0 >> >> thank you in advance >> >> anett >> >> -- >> ImageJ mailing list: http://imagej.nih.gov/ij/list.html >> > > > > -- > Ignacio Arganda-Carreras, Ph.D. > Seung's lab, 46-5065 > Department of Brain and Cognitive Sciences > Massachusetts Institute of Technology > 43 Vassar St. > Cambridge, MA 02139 > USA > > Phone: (001) 617-324-3747 > Website: http://bioweb.cnb.csic.es/~iarganda/index_EN.html > -- Ignacio Arganda-Carreras, Ph.D. Seung's lab, 46-5065 Department of Brain and Cognitive Sciences Massachusetts Institute of Technology 43 Vassar St. Cambridge, MA 02139 USA Phone: (001) 617-324-3747 Website: http://bioweb.cnb.csic.es/~iarganda/index_EN.html -- ImageJ mailing list: http://imagej.nih.gov/ij/list.html |
|
|
Hello Ignacio,
thanks a lot it works!! ta! Anett Zitat von Ignacio Arganda-Carreras <[hidden email]>: > Please, update Fiji, I just released a version that fix the bug. > > Cheers! > > ignacio > > On Wed, Sep 24, 2014 at 2:18 PM, Ignacio Arganda-Carreras < > [hidden email]> wrote: > >> Hello Anett, >> >> Did you select the "Allow multiple foreground components" option in the >> GUI? >> >> This is somehow a bug, because when you applied the saved segmentator it >> looks for multiple foreground objects even if you didn't want to. >> >> ignacio >> >> On Wed, Sep 24, 2014 at 12:58 PM, Anett Jannasch < >> [hidden email]> wrote: >> >>> hi, >>> >>> I have problems using the siox plugin. The mask I create and save based >>> on my RGB picture is not the same (result is different) when i apply this >>> mask to this RGB picture. Has anyone an idea or observed similar problems? >>> >>> picture and wrong masks you can find here: >>> >>> https://www.dropbox.com/s/jct64wudgbxxcoc/Fiji%20siox%20bug.pptx?dl=0 >>> https://www.dropbox.com/s/daew3gbhfnpp10m/G23_1_SMA_1_800_250613a.zvi?dl=0 >>> >>> thank you in advance >>> >>> anett >>> >>> -- >>> ImageJ mailing list: http://imagej.nih.gov/ij/list.html >>> >> >> >> >> -- >> Ignacio Arganda-Carreras, Ph.D. >> Seung's lab, 46-5065 >> Department of Brain and Cognitive Sciences >> Massachusetts Institute of Technology >> 43 Vassar St. >> Cambridge, MA 02139 >> USA >> >> Phone: (001) 617-324-3747 >> Website: http://bioweb.cnb.csic.es/~iarganda/index_EN.html >> > > > > -- > Ignacio Arganda-Carreras, Ph.D. > Seung's lab, 46-5065 > Department of Brain and Cognitive Sciences > Massachusetts Institute of Technology > 43 Vassar St. > Cambridge, MA 02139 > USA > > Phone: (001) 617-324-3747 > Website: http://bioweb.cnb.csic.es/~iarganda/index_EN.html > > -- > ImageJ mailing list: http://imagej.nih.gov/ij/list.html Wissenschaftliche Mitarbeiterin Klinik für Herzchirurgie Herzzentrum Dresden GmbH Universitätsklinik der technischen Universität Dresden Fetscherstraße 76 01307 Dresden Tel.: ++49 351 450 1090 email: [hidden email] -- ImageJ mailing list: http://imagej.nih.gov/ij/list.html |
Re: bug siox segmentation?
|
|
No worries, Anett.
Just remember that when you use the SIOX GUI, you select your background regions by hand and that information is used in the segmentation. However, when you load the SIOX segmentator and apply it to the new images, only the color information is used. So the results might be slightly different. I chose to preserve the largest foreground object found by the algorithm, which is usually what the user expects. Best, ignacio On Fri, Sep 26, 2014 at 9:17 AM, Anett Jannasch < [hidden email]> wrote: > Hello Ignacio, > > thanks a lot it works!! > > ta! > > Anett > > > Zitat von Ignacio Arganda-Carreras <[hidden email]>: > > > Please, update Fiji, I just released a version that fix the bug. >> >> Cheers! >> >> ignacio >> >> On Wed, Sep 24, 2014 at 2:18 PM, Ignacio Arganda-Carreras < >> [hidden email]> wrote: >> >> Hello Anett, >>> >>> Did you select the "Allow multiple foreground components" option in the >>> GUI? >>> >>> This is somehow a bug, because when you applied the saved segmentator it >>> looks for multiple foreground objects even if you didn't want to. >>> >>> ignacio >>> >>> On Wed, Sep 24, 2014 at 12:58 PM, Anett Jannasch < >>> [hidden email]> wrote: >>> >>> hi, >>>> >>>> I have problems using the siox plugin. The mask I create and save based >>>> on my RGB picture is not the same (result is different) when i apply >>>> this >>>> mask to this RGB picture. Has anyone an idea or observed similar >>>> problems? >>>> >>>> picture and wrong masks you can find here: >>>> >>>> https://www.dropbox.com/s/jct64wudgbxxcoc/Fiji%20siox%20bug.pptx?dl=0 >>>> https://www.dropbox.com/s/daew3gbhfnpp10m/G23_1_SMA_1_ >>>> 800_250613a.zvi?dl=0 >>>> >>>> thank you in advance >>>> >>>> anett >>>> >>>> -- >>>> ImageJ mailing list: http://imagej.nih.gov/ij/list.html >>>> >>>> >>> >>> >>> -- >>> Ignacio Arganda-Carreras, Ph.D. >>> Seung's lab, 46-5065 >>> Department of Brain and Cognitive Sciences >>> Massachusetts Institute of Technology >>> 43 Vassar St. >>> Cambridge, MA 02139 >>> USA >>> >>> Phone: (001) 617-324-3747 >>> Website: http://bioweb.cnb.csic.es/~iarganda/index_EN.html >>> >>> >> >> >> -- >> Ignacio Arganda-Carreras, Ph.D. >> Seung's lab, 46-5065 >> Department of Brain and Cognitive Sciences >> Massachusetts Institute of Technology >> 43 Vassar St. >> Cambridge, MA 02139 >> USA >> >> Phone: (001) 617-324-3747 >> Website: http://bioweb.cnb.csic.es/~iarganda/index_EN.html >> >> -- >> ImageJ mailing list: http://imagej.nih.gov/ij/list.html >> > > > > Wissenschaftliche Mitarbeiterin > Klinik für Herzchirurgie > Herzzentrum Dresden GmbH > Universitätsklinik der technischen Universität Dresden > Fetscherstraße 76 > > 01307 Dresden > > Tel.: ++49 351 450 1090 > email: [hidden email] > > > -- > ImageJ mailing list: http://imagej.nih.gov/ij/list.html > > -- > Ignacio Arganda-Carreras, Ph.D. > Seung's lab, 46-5065 > Department of Brain and Cognitive Sciences > Massachusetts Institute of Technology > 43 Vassar St. > Cambridge, MA 02139 > USA > > Phone: (001) 617-324-3747 > Website: <http://imagej.nih.gov/ij/list.html> > http://bioweb.cnb.csic.es/~iarganda/index_EN.html > -- ImageJ mailing list: http://imagej.nih.gov/ij/list.html |
«
Return to ImageJ
|
1 view|%1 views
| Free forum by Nabble | Edit this page |