Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add menu clickorder to fiji lookuptable change #234

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Add menu clickorder to fiji lookuptable change #234

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion documentation/basics/common_problems.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ ilastik works best if the input data is in the hdf5 format. Here are some option
* Write a custom script in Python using the h5py library

#### 4) My exported results are all black!
ilastik exports probability maps or segmentations. The former have a range from 0 to 1 and by default they are of type float. This is convenient for automatic post-processing, but not for visual inspection. To export as a viewable image, change the output type to ``unsigned int, 8 bit`` and renormalize the range from (0, 1) to (0, 255). More details on these operations can be found [here]({{site.baseurl}}/documentation/basics/export#settings). If you are exporting a segmentation, ilastik saves it as a labeled image, so every pixel has the value of the most probable label found during classification. If you had, say, 3 labels, your image is composed of values 1, 2 and 3, which looks black if viewed raw. An image like this should be displayed with a ``lookup table``. For example, ``glasbey`` LUT in Fiji usually works well, but you can also define your own if you have specific class colors in mind.
ilastik exports probability maps or segmentations. The former have a range from 0 to 1 and by default they are of type float. This is convenient for automatic post-processing, but not for visual inspection. To export as a viewable image, change the output type to ``unsigned int, 8 bit`` and renormalize the range from (0, 1) to (0, 255). More details on these operations can be found [here]({{site.baseurl}}/documentation/basics/export#settings). If you are exporting a segmentation, ilastik saves it as a labeled image, so every pixel has the value of the most probable label found during classification. If you had, say, 3 labels, your image is composed of values 1, 2 and 3, which looks black if viewed raw. An image like this should be displayed with a ``lookup table``. For example, ``glasbey`` LUT in Fiji usually works well (_Image_ -> _Lookup Tables_ -> _glasbey_), but you can also define your own if you have specific class colors in mind.

#### 5) Can I just select all features?
For [Pixel Classification workflow]({{site.baseurl}}/documentation/pixelclassification/pixelclassification) you can select all. In theory and in our own practice, there should be no negative effect on the classification accuracy. However, computing more pixel features is slower than computing less.
Expand Down