table of contents
mia-2dsegment-local-kmeans(1) | General Commands Manual | mia-2dsegment-local-kmeans(1) |
NAME¶
mia-2dsegment-local-kmeans - Run a k-means segmentation of a 2D image.
SYNOPSIS¶
mia-2dsegment-local-kmeans -i <in-file> [options]
DESCRIPTION¶
mia-2dsegment-local-kmeans This program runs the segmentation of a 2D image by applying a localized k-means approach that helps to overcome intensity inhomogeneities in the image. The approach evaluates a global k-means clustering, and then separates the image into overlapping regions where more k-means iterations are run only including the locally present classes, i.e. the classes that relatively contain more pixels than a given threshold.
OPTIONS¶
File-IO¶
- -i --in-file=(input, required); io
- image to be segmented
For supported file types see PLUGINS:2dimage/io - -o --out-file=(output); io
- class label image based on merging local labels
For supported file types see PLUGINS:2dimage/io - -O --out-file2=(output); io
- class label image based on classifying by using the interpolated class
centers
For supported file types see PLUGINS:2dimage/io - -D --debug-centers=(output); io
- Save the class center images to a debug file (type is double)
For supported file types see PLUGINS:2dimage/io
Help & Info¶
- -V --verbose=warning
- verbosity of output, print messages of given level and higher priorities. Supported priorities starting at lowest level are:
- --copyright
- print copyright information
- -h --help
- print this help
- -? --usage
- print a short help
- --version
- print the version number and exit
Parameters¶
- -g --grid-spacing=20; int in [3, inf)
- Spacing of the grid used to modulate the intensity inhomogeneities
- -n --nclasses=3; uint in [2, 127]
- Number of intensity classes to segment
- -t --relative-cluster-threshold=0.0001; double in [0, 1)
- Number of intensity classes to segment
Processing¶
- --threads=-1
- Maxiumum number of threads to use for processing,This number should be lower or equal to the number of logical processor cores in the machine. (-1: automatic estimation).
PLUGINS: 2dimage/io¶
- bmp
- BMP 2D-image input/output support. The plug-in supports reading and writing of binary images and 8-bit gray scale images. read-only support is provided for 4-bit gray scale images. The color table is ignored and the pixel values are taken as literal gray scale values.
- datapool
- Virtual IO to and from the internal data pool
- dicom
- 2D image io for DICOM
- exr
- a 2dimage io plugin for OpenEXR images
- jpg
- a 2dimage io plugin for jpeg gray scale images
- png
- a 2dimage io plugin for png images
- raw
- RAW 2D-image output support
- tif
- TIFF 2D-image input/output support
- vista
- a 2dimage io plugin for vista images
EXAMPLE¶
Run the segmentation on image test.png using three classes, local regions of 40 pixels (grid width 20 pixels), and a class ignore threshold of 0.01.
mia-2dsegment-local-kmeans -i test.png -o label.png -n 3 -g 20 -t 0.01
AUTHOR(s)¶
Gert Wollny
COPYRIGHT¶
This software is Copyright (c) 1999‐2015 Leipzig, Germany and Madrid, Spain. It comes with ABSOLUTELY NO WARRANTY and you may redistribute it under the terms of the GNU GENERAL PUBLIC LICENSE Version 3 (or later). For more information run the program with the option '--copyright'.
v2.4.7 | USER COMMANDS |