Code Monkey home page Code Monkey logo

multitemplatematching-fiji's Introduction

DOI Twitter Follow

Installation

Via the Fiji updater

Tick the Multi-Template-Matching AND IJ-OpenCV update site of the Fiji udpater.
A new entry will show up in the Plugin Menu (all the way down) after restarting Fiji.
See how to activate an update site.

Manual installation

You can also do a manual installation by copying the files in the right place.
This can be useful if you would like to use a previous version that is not available via the update site, but which is archived in the releases tab.
You still need to tick the IJ-OpenCV update site in the Fiji updater to install the dependencies.

Then you can download the files either on the main page above this readme, by clicking the green button with the arrow pointing down Code then Download ZIP.
You can download the zip of previous versions on the release tab, below asset select Source code (zip).
Unzip the zip file, and on Windows, drag the folder Fiji.app from the unzipped directory, and drop it on the directory Fiji.app of your existing Fiji installation.
The idea is to merge both Fiji.app directories, in Windows this drag and dropping will automatically copy the files in the corresponding subdirectories.
Restart Fiji then.
If the drag and dropping does not work for you, you just have to copy the files from the unzziped directory to the corresponding directories in your Fiji installation.
If some directories (ex: Lib in Fiji.app/jars) does not exist, just create them.

Documentation

Template matching is an algorithm that can be used for object-detections in images.
The algorithm computes the probability to find one (or several) template images provided by the user.
See the wiki section for the documentation, or the website of the project.

You can find a similar implementation in:

Video tutorial

Playlist on YouTube
Tuto

Citation

If you use this implementation for your research, please cite:

Thomas, L.S.V., Gehrig, J. Multi-template matching: a versatile tool for object-localization in microscopy images.
BMC Bioinformatics 21, 44 (2020). https://doi.org/10.1186/s12859-020-3363-7

Download the citation as a .ris file from the journal website, here.

Related resources

IJ-OpenCV

This plugin is using OpenCV in Fiji thanks to IJ-OpenCV.

see also:
Domínguez, César, Jónathan Heras, and Vico Pascual. "IJ-OpenCV: Combining ImageJ and OpenCV for processing images in biomedicine." Computers in biology and medicine 84 (2017): 189-194.

Licence

Creative Commons License
The content of this wiki (including illustrations and videos) is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

As a derived work of IJ-OpenCV, the source codes are licensed under GPL-3.

Origin of the work

This work has been part of the PhD project of Laurent Thomas under supervision of Dr. Jochen Gehrig at ACQUIFER.

Fish

Funding

This project has received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No 721537 ImageInLife.

ImageInLife MarieCurie

Examples

Zebrafish head detection

Fish

MontageHead

Dataset available on Zenodo
DOI

Medaka larvae detections

MedakaEgg

MontageEgg

Image courtesy Jakob Gierten (COS, Heidelberg)
Dataset available on Zenodo
DOI

multitemplatematching-fiji's People

Contributors

laulauthom avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar

multitemplatematching-fiji's Issues

ListImage plugin not macro-recordable

The multi-file input is not correctly recorded, it returns the File object identifier.
run("Template Matching ListImage", "template_files=[Ljava.io.File;@6b113364 image_files=[Ljava.io.File;@2db91c40 flipv=false fliph=false method=[Normalised 0-mean cross-correlation] n_hit=4 score_threshold=0.4 max_overlap=0.8000001 show_images=true add_roi=true show_table=true");

No module named bytedeco

-> Make sure that you have activated the IJ-OpenCV update site to have all dependencies necessary

Activating the IJ-OpenCV wont be necessary by using a pom.xml with Maven, once this bug is fixed

How did you organised a multi-script python program for ImageJ?

I understand this question is not really an "issue", but this is the first project that I have seen that managed to use multiple *.py scripts for one plugin. Indeed, this is something I would like to do myself but I am still struggling to find the way. I know that if I drop a *.py file to the /jars/Libs folder, these will be transformed into $*.class files so that I can call the functions in there. However, if instead of a file I drop a folder with several files, they become invisible. Finally, I would like to ask how did you manage to organise the installation logic as you said that by "merging" the Fiji.app folder with the "MultiTemplateMatching-Fiji" folder places all the scripts in the right place.

opencv not found after installation via update site

Hi,
I have followed the installation procedure via the Fiji updater.
I can see that IJ-opencv and multi-template-matching are installed (as they appear in the plugins dropdown menu).

However, when I run the Template Matching Image function, I have an error saying that the OpenCV dependencies are missing and the following error is raised:
java.lang.NoClassDefFoundError: java.lang.NoClassDefFoundError: Could not initialize class org.bytedeco.javacpp.opencv_core

System:
macOS 12.6.3
Fiji 2.9.0/1.53t

Folder mode not working any more

Hi,
I've been using your excellent plugin successfully until now. After the new update to 1.53c, the Folder mode doesn't work any more. When I set everything up and run it, it stops immediately, saying that it's done, even though nothing was computed. There is no error message. The Image and ListImage modes are still fine. I'm using Windows 10.
Many thanks for any suggestion,

Zoltan

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.