ImageJ version of FogBank?
Locked
 
|
A bit over a year ago, there was a thread that mentioned FogBank (for
segmentation of phase images) https://isg.nist.gov/deepzoomweb/resources/csmet/pages/fogbank_segmentation/fogbank_segmentation.html and https://list.nih.gov/cgi-bin/wa.exe?A2=ind1608&L=IMAGEJ&P=R12059&1=IMAGEJ&9=A&J=on&d=No+Match%3BMatch%3BMatches&z=4 Since then, has anyone ported this to ImageJ ? Alternatively, can someone who has run this with mcr on macos can tell me how to do that. (assuming it can be done on macos). I downloaded the Matlab runtime compiler, but I cannot figure out how to get it to do anything. There is documentation about how to set the paths, which I could not follow. Since there is a lot of matlab expertise on this list, maybe someone who has done it can tell me how to set it up. Thanks in advance --aryeh -- Aryeh Weiss Faculty of Engineering Bar Ilan University Ramat Gan 52900 Israel Ph: 972-3-5317638 FAX: 972-3-7384051 -- ImageJ mailing list: http://imagej.nih.gov/ij/list.html |
Re: ImageJ version of FogBank?
|
|
On Sunday, 12 November 2017 07:21:29 GMT [hidden email] wrote:
> A bit over a year ago, there was a thread that mentioned FogBank (for > segmentation of phase images) > https://isg.nist.gov/deepzoomweb/resources/csmet/pages/fogbank_segmentation/ > fogbank_segmentation.html > > and > https://list.nih.gov/cgi-bin/wa.exe?A2=ind1608&L=IMAGEJ&P=R12059&1=IMAGEJ&9= > A&J=on&d=No+Match%3BMatch%3BMatches&z=4 > > Since then, has anyone ported this to ImageJ ? Hi Aryeh, I remember at the time having a look at the paper. It reminds me of the marker-controlled segmentation: https://uk.mathworks.com/help/images/examples/marker-controlled-watershed-segmentation.html The fogbank paper seems to use the dark regions as seeds and some detectable cell boundaries as barriers, which is somewhat similar to what the above does. There might be other differences, but in the absence of plugins, maybe the above is easier to implement? Cheers Gabriel -- ImageJ mailing list: http://imagej.nih.gov/ij/list.html |
Re: ImageJ version of FogBank?
|
|
In reply to this post by Aryeh Weiss
There is no official ImageJ/Fiji implementation of Fogbank. However, I do not know if another developer has ported the Matlab code independently.
Generally, the easiest way to run Fogbank is to download the source code and run it directly in Matlab (if you have a license). If you don't have a Matlab license, download MCR 9.1 (R2016b) which was used to compile the latest executable available on the project page. With MCR 9.1 installed, you should be able to run the compiled executable on Windows. Aryeh Weiss, Once you installed the MCR were you able to run the executable version of Fogbank? I just want to confirm that the problem is with the macros, and not with the executable directly. I can help with problems w.r.t. the executable, but I have no experience integrating with macros. -Michael Majurski Links: Github repo for Matlab code: https://github.com/usnistgov/FogBank Project Page: https://isg.nist.gov/deepzoomweb/resources/csmet/pages/fogbank_segmentation/fogbank_segmentation.html Fogbank Wiki: https://github.com/usnistgov/FogBank/wiki On 2017-11-12, 02:34, "Aryeh Weiss" <[hidden email]> wrote: A bit over a year ago, there was a thread that mentioned FogBank (for segmentation of phase images) https://isg.nist.gov/deepzoomweb/resources/csmet/pages/fogbank_segmentation/fogbank_segmentation.html and https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Flist.nih.gov%2Fcgi-bin%2Fwa.exe%3FA2%3Dind1608%26L%3DIMAGEJ%26P%3DR12059%261%3DIMAGEJ%269%3DA%26J%3Don%26d%3DNo%2BMatch%253BMatch%253BMatches%26z%3D4&data=02%7C01%7Cmichael.majurski%40nist.gov%7C947b30faa1294958f2dc08d5299fb4f3%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C1%7C636460688283844104&sdata=QVTcyvRvhOCT8%2FTrQwR%2BDlXVb6H4wSmNFUVCHtrcn9M%3D&reserved=0 Since then, has anyone ported this to ImageJ ? Alternatively, can someone who has run this with mcr on macos can tell me how to do that. (assuming it can be done on macos). I downloaded the Matlab runtime compiler, but I cannot figure out how to get it to do anything. There is documentation about how to set the paths, which I could not follow. Since there is a lot of matlab expertise on this list, maybe someone who has done it can tell me how to set it up. Thanks in advance --aryeh -- Aryeh Weiss Faculty of Engineering Bar Ilan University Ramat Gan 52900 Israel Ph: 972-3-5317638 FAX: 972-3-7384051 -- ImageJ mailing list: https://na01.safelinks.protection.outlook.com/?url=http%3A%2F%2Fimagej.nih.gov%2Fij%2Flist.html&data=02%7C01%7Cmichael.majurski%40nist.gov%7C947b30faa1294958f2dc08d5299fb4f3%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C0%7C636460688283854117&sdata=o2Q9uFmAH03hprOiggiYBeWTXwN%2FON6bNR87BJW2r7c%3D&reserved=0 -- ImageJ mailing list: http://imagej.nih.gov/ij/list.html |
|
|
In reply to this post by Gabriel Landini
On 12/11/2017 13:58, Gabriel Landini wrote:
> On Sunday, 12 November 2017 07:21:29 GMT [hidden email] wrote: >> A bit over a year ago, there was a thread that mentioned FogBank (for >> segmentation of phase images) >> https://isg.nist.gov/deepzoomweb/resources/csmet/pages/fogbank_segmentation/ >> fogbank_segmentation.html >> >> and >> https://list.nih.gov/cgi-bin/wa.exe?A2=ind1608&L=IMAGEJ&P=R12059&1=IMAGEJ&9= >> A&J=on&d=No+Match%3BMatch%3BMatches&z=4 >> >> Since then, has anyone ported this to ImageJ ? > Hi Aryeh, > I remember at the time having a look at the paper. > It reminds me of the marker-controlled segmentation: > https://uk.mathworks.com/help/images/examples/marker-controlled-watershed-segmentation.html > > The fogbank paper seems to use the dark regions as seeds and some detectable > cell boundaries as barriers, which is somewhat similar to what the above does. > There might be other differences, but in the absence of plugins, maybe the > above is easier to implement? > Thanks for your reply. I agree that they probably based it on marker controlled segmentation, combined whatever borders could be detected. I figure that they already dealt with various optimizations that these things often need, so I was hoping to run FogBank before doing it myself. Best regards --aryeh -- Aryeh Weiss Faculty of Engineering Bar Ilan University Ramat Gan 52900 Israel Ph: 972-3-5317638 FAX: 972-3-7384051 -- ImageJ mailing list: http://imagej.nih.gov/ij/list.html |
|
|
In reply to this post by Majurski, Michael Paul (Fed)
Thank you fr your detailed reply.
On 12/11/2017 19:49, Majurski, Michael Paul (Fed) wrote: > There is no official ImageJ/Fiji implementation of Fogbank. However, I do not know if another developer has ported the Matlab code independently. > > Generally, the easiest way to run Fogbank is to download the source code and run it directly in Matlab (if you have a license). > > If you don't have a Matlab license, download MCR 9.1 (R2016b) which was used to compile the latest executable available on the project page. With MCR 9.1 installed, you should be able to run the compiled executable on Windows. I understand form this that their is no executable for macos. I have not tried running it on Windows, since I have a mac. I can try it with VirtualBox, but that will have to wait until I have a chance to set that up. > Aryeh Weiss, > Once you installed the MCR were you able to run the executable version of Fogbank? No, but that is probably because I the executable is for Windows, and I am running on a mac. > I just want to confirm that the problem is with the macros, and not with the executable directly. I can help with problems w.r.t. the executable, but I have no experience integrating with macros. Many thanks. When I have time to try it under windows, I will update on whether it worked. Best regards --aryeh > -Michael Majurski > > > Links: > Github repo for Matlab code: > https://github.com/usnistgov/FogBank > > Project Page: > https://isg.nist.gov/deepzoomweb/resources/csmet/pages/fogbank_segmentation/fogbank_segmentation.html > > Fogbank Wiki: > https://github.com/usnistgov/FogBank/wiki > > > > On 2017-11-12, 02:34, "Aryeh Weiss" <[hidden email]> wrote: > > A bit over a year ago, there was a thread that mentioned FogBank (for > segmentation of phase images) > https://isg.nist.gov/deepzoomweb/resources/csmet/pages/fogbank_segmentation/fogbank_segmentation.html > > and > https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Flist.nih.gov%2Fcgi-bin%2Fwa.exe%3FA2%3Dind1608%26L%3DIMAGEJ%26P%3DR12059%261%3DIMAGEJ%269%3DA%26J%3Don%26d%3DNo%2BMatch%253BMatch%253BMatches%26z%3D4&data=02%7C01%7Cmichael.majurski%40nist.gov%7C947b30faa1294958f2dc08d5299fb4f3%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C1%7C636460688283844104&sdata=QVTcyvRvhOCT8%2FTrQwR%2BDlXVb6H4wSmNFUVCHtrcn9M%3D&reserved=0 > > Since then, has anyone ported this to ImageJ ? > > Alternatively, can someone who has run this with mcr on macos can tell > me how to do that. (assuming it can be done on macos). I downloaded the > Matlab runtime compiler, but I cannot figure out how to get it to do > anything. There is documentation about how to set the paths, which I > could not follow. > Since there is a lot of matlab expertise on this list, maybe someone who > has done it can tell me how to set it up. > > Thanks in advance > --aryeh > > -- > Aryeh Weiss > Faculty of Engineering > Bar Ilan University > Ramat Gan 52900 Israel > > Ph: 972-3-5317638 > FAX: 972-3-7384051 > > > -- > ImageJ mailing list: https://na01.safelinks.protection.outlook.com/?url=http%3A%2F%2Fimagej.nih.gov%2Fij%2Flist.html&data=02%7C01%7Cmichael.majurski%40nist.gov%7C947b30faa1294958f2dc08d5299fb4f3%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C0%7C636460688283854117&sdata=o2Q9uFmAH03hprOiggiYBeWTXwN%2FON6bNR87BJW2r7c%3D&reserved=0 > > > > -- > ImageJ mailing list: http://imagej.nih.gov/ij/list.html -- Aryeh Weiss Faculty of Engineering Bar Ilan University Ramat Gan 52900 Israel Ph: 972-3-5317638 FAX: 972-3-7384051 -- ImageJ mailing list: http://imagej.nih.gov/ij/list.html |
«
Return to ImageJ
|
1 view|%1 views
| Free forum by Nabble | Edit this page |