From 833bbbfe375457bafa8efc2688df784057bf91d0 Mon Sep 17 00:00:00 2001 From: Dominik Kutra Date: Mon, 6 Mar 2023 13:29:12 +0100 Subject: [PATCH] Add menu clickorder to fiji lookuptable change --- documentation/basics/common_problems.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/documentation/basics/common_problems.md b/documentation/basics/common_problems.md index 2888a45..b00a095 100644 --- a/documentation/basics/common_problems.md +++ b/documentation/basics/common_problems.md @@ -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.