Summary

• Page properties (1 modified, 0 added, 0 removed)

Details

Page properties

Content

...	...	@@ -9,30 +9,25 @@
9	9
10	10	As a general rule, pixel classification is suitable for images in which there are clear differences in the colour, intensity and/ or texture of the feature-of-interest versus the background and other structures.  If there is non-specific labelling in the image that is very similar in appearance to the labelling-of-interest, object classification may allow the non-specific labelling to be filtered out based on object level features such as size and shape. The best approach is determined by trial and error.
11	11
12		-=== Pixel classification workflow ===
13	13
14		-For a quick introduction, watch: [[https:~~/~~/www.youtube.com/watch?v=5N0XYW9gRZY&feature=youtu.be>>url:https://www.youtube.com/watch?v=5N0XYW9gRZY&feature=youtu.be]]
	13	+=== H3 Headings Will Appear In The Table of Content ===
15	15
16		-**Basic steps:**
	15	+==== You can also add images ====
17	17
18		--Train the classifier with two classes (labeling and background)
	17	+[[image:Collaboratory.Apps.Article.Code.ArticleSheet@placeholder.jpg]]
19	19
20		--Apply the classifier to the rest of the images (Batch processing)
	19	+Photo by David Clode
21	21
22		--Export the probability maps in HDH5 format, and simple_segmentation images in .png format, with the default settings.
	21	+==== Or code ====
23	23
24		-=== Object classification workflow ===
	23	+Code blocks can be added by using the code macro:
25	25
26		-There are three options on the ilastik start up page for running Object Classification.  Choose the //Object Classification with Raw Data and Pixel Prediction Maps as input//**.**
	25	+{{code language="python"}}
	26	+x = 1
	27	+if x == 1:
	28	+ # indented four spaces
	29	+ print("x is 1.")
	30	+{{/code}}
27	27
28		--Save the object classification file in the same folder as the raw images for analysis.  If the images are moved after the ilastik file is created, the link between the ilastik file and the images may be lost, resulting in a corrupted file.
29		-
30		--In the **Input Data** applet, upload the original images and their respective probability maps in HDH5 format (output from the pixel classification).
31		-
32		--Train the classifier with two classes (labeling and artefacts)
33		-
34		-(% class="wikigeneratedid" id="H" %)
35		--In the **Object Information Export** applet, export “Object Predictions” in PNG format.  Do not change the default export location
36		-
37		-
	32	+(% class="wikigeneratedid" id="HH4Won27tAppearinToC" %)
38	38