Skip to content, Skip to search

Changes

Microscope Focus Quality

1,845 bytes added, 13:29, 31 August 2017
Add initial page with minimal information
[[File:Mifqc.png|900px]]
{{Component
| name = Microscope Image Focus Quality Classifier
| url = https://imagej.net/Microscope_Focus_Quality
| source = {{GitHub | org=fiji | repo=microscope-image-quality | tag=microscope-image-quality-0.1.0}}
| license = [[Apache]]
| release = {{Maven | g=sc.fiji | a=microscope-image-quality | v=0.1.0 | label=0.1.0}}
| devStatus = {{DevStatus | developer=yes | incubating=yes | obsolete=no}}
| supportStatus = {{SupportStatus | debugger=yes | reviewer=yes | support=yes}}
| founders = {{Person|ctrueden}}, {{Person|samueljyang}}, {{Person|asimshankar}}
| leads = {{Person|ctrueden}}
| developers = {{Person|ctrueden}}
| debuggers = {{Person|ctrueden}}
| reviewers = {{Person|ctrueden}}
| support = {{Person|ctrueden}}
| maintainers = {{Person|ctrueden}}
| contributors = {{Person|samueljyang}}, {{Person|asimshankar}}
}}This plugin assesses the focus quality of microscope images, classifying the image in tiles.

== Summary ==

The plugin predicts an absolute measure of image focus on a single image in isolation, without any user-specified parameters. It uses a pre-trained deep neural network, operating at the image-patch level, and also outputs a measure of prediction certainty, enabling interpretable predictions.

== Installation ==

* [[Following an update site|Enable]] the TensorFlow [[update site]].
* The command is in {{bc | Classification | Microscope Image Focus Quality}}.

== Limitations ==

The plugin is currently limited to 16-bit integer data only. The model was trained with images in the intensity range of <code>[0, ~10000]</code>; your mileage may vary if the input image intensities diverge from that too greatly.

== Publication ==

* {{Publication | Microscope Image Quality}}

== See also ==

* [[TensorFlow]], the machine learning library this plugin uses.

[[Category:Citable]]
Bureaucrat, emailconfirmed, incoming, administrator, uploaders
11,810
edits