Lorensen at 17:01, 23 April 2010

2010-04-23T17:01:55Z

Lorensen: /* Usage */

2010-04-23T16:55:37Z

Usage

Lorensen: Created page with 'Return to Slicer 3.6 Documentation NOTOC ===Module Name=== Otsu Threshold Segmentation == General Information == ===Module Type & Category=== Type: …'

2010-04-23T16:49:52Z

Created page with 'Return to Slicer 3.6 Documentation __NOTOC__ ===Module Name=== Otsu Threshold Segmentation == General Information == ===Module Type & Category=== Type: …'

New page

[[Documentation-3.6|Return to Slicer 3.6 Documentation]]

__NOTOC__
===Module Name===
Otsu Threshold Segmentation

== General Information ==
===Module Type & Category===

Type: CLI

Category: Segmentation

===Authors, Collaborators & Contact===
* Author: Bill Lorensen
* Contact: bill.lorensen at gmail.com

===Module Description===
This filter creates a labeled image from a grayscale image.
First, it calculates an optimal threshold that separates the image into
foreground and background. This threshold separates those two classes so
that their intra-class variance is minimal (see
http://en.wikipedia.org/wiki/Otsu%27s_method). Then the filter runs a
connected component algorithm to generate unique labels for each
connected region of the foreground. Finally, the resulting image is
relabeled to provide consequetive numbering.

The original reference is:
N.Otsu, ‘‘A threshold selection method from gray level histograms,’’
IEEE Trans.Syst.ManCybern.SMC-9,62–66 1979.

== Usage ==
<pre>
OtsuThresholdSegmentation [--returnparameterfile
<std::string>]
[--processinformationaddress
<std::string>] [--xml] [--echo]
[--minimumObjectSize <int>]
[--faceConnected] [--numberOfBins
<int>] [--brightObjects] [--]
[--version] [-h] <std::string>
<std::string>
Where:
--returnparameterfile <std::string>
Filename in which to write simple return parameters (int, float,
int-vector, etc.) as opposed to bulk return parameters (image,
geometry, transform, measurement, table).
--processinformationaddress <std::string>
Address of a structure to store process information (progress, abort,
etc.). (default: 0)
--xml
Produce xml description of command line arguments (default: 0)
--echo
Echo the command line arguments (default: 0)
--minimumObjectSize <int>
Minimum size of object to retain. This parameter can be used to get
rid of small regions in noisy images. (default: 0)
--faceConnected
This is an advanced parameter. Adjacent voxels are face connected.
This affects the connected component algorithm. If this parameter is
flase, more regions are likely to be identified. (default: 0)
--numberOfBins <int>
This is an advanced parameter. The number of bins in the histogram
used to model the probability mass function of the two intensity
distributions. Small numbers of bins may result in a more conservative
threshold. The default should suffice for most applications.
Experimentation is the only way to see the effect of varying this
parameter. (default: 128)
--brightObjects
Segmenting bright objects on a dark background or dark objects on a
bright background. (default: 0)
--, --ignore_rest
Ignores the rest of the labeled arguments following this flag.
--version
Displays version information and exits.
-h, --help
Displays usage information and exits.
<std::string>
(required) Input volume to be segmented
<std::string>
(required) Output filtered
</pre>

===Source code & documentation===

Source Code: [http://www.na-mic.org/ViewVC/index.cgi/trunk/Applications/CLI/OtsuThresholdSegmentation.cxx?view=co OtsuThresholdSegmentation.cxx]

XML Description: [http://www.na-mic.org/ViewVC/index.cgi/trunk/Applications/CLI/OtsuThresholdSegmentation.xml?view=co OtsuThresholdSegmentation.xml]

== More Information ==

===Acknowledgement===
This work is part of the National Alliance for Medical Image
Computing (NAMIC), funded by the National Institutes of Health
through the NIH Roadmap for Medical Research, Grant U54 EB005149.
Information on the National Centers for Biomedical Computing
can be obtained from [http://www.ncbcs.org/ National Centers for Biomedical Computing].

===References===

* http://en.wikipedia.org/wiki/Otsu%27s_method
* http://www.labbookpages.co.uk/software/imgProc/otsuThreshold.html
* N.Otsu, [http://web.ics.purdue.edu/~kim497/ece661/OTSU_paper.pdf ‘‘A threshold selection method from gray level histograms,’’ IEEE Trans.Syst.ManCybern.SMC-9,62–66 1979.]

@@ Line 25: / Line 25: @@
 connected component algorithm to generate unique labels for each
 connected region of the foreground. Finally, the resulting image is
-relabeled to provide consequetive numbering.
+relabeled to provide consecutive numbering.
 The original reference is:

@@ Line 33: / Line 33: @@
 == Usage ==
 <pre>
-  OtsuThresholdSegmentation  [--returnparameterfile
+  OtsuThresholdSegmentation [--returnparameterfile
                             <std::string>]
                             [--processinformationaddress
@@ Line 60: / Line 60: @@
       This is an advanced parameter. Adjacent voxels are face connected.
       This affects the connected component algorithm. If this parameter is
-      flase, more regions are likely to be identified. (default: 0)
+      false, more regions are likely to be identified. (default: 0)
     --numberOfBins <int>
       This is an advanced parameter. The number of bins in the histogram

Modules:OtsuThresholdSegmentation-Documentation-3.6 - Revision history

Lorensen at 17:01, 23 April 2010

Lorensen: /* Usage */

Lorensen: Created page with 'Return to Slicer 3.6 Documentation __NOTOC__ ===Module Name=== Otsu Threshold Segmentation == General Information == ===Module Type & Category=== Type: …'

Lorensen: Created page with 'Return to Slicer 3.6 Documentation NOTOC ===Module Name=== Otsu Threshold Segmentation == General Information == ===Module Type & Category=== Type: …'