A contrario segmentation: Acsegmentor

Research.Acsegmentor History

Show minor edits - Show changes to output

May 26, 2014, at 03:46 AM by 208.66.25.130 -
Deleted lines 4-6:

Contact: mailto:nicolas.burrus@gmail.com

May 26, 2014, at 03:46 AM by 208.66.25.130 -
Changed lines 6-7 from:
Contact: mailto:Nicolas.Burrus@uc3m.es
to:
Contact: mailto:nicolas.burrus@gmail.com
Changed lines 6-7 from:
Contact: mailto:Nicolas.Burrus@ensta.fr
to:
Contact: mailto:Nicolas.Burrus@uc3m.es
January 18, 2009, at 06:17 PM by 81.240.213.170 -
Changed line 23 from:
** Source [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.2.0a-Source.tar.bz2|acsegmentor-0.2.0a-Source.tar.bz2]] or [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.2.0a-Source.zip|acsegmentor-0.2.0a-Source.zip]] (bigger)
to:
** Source [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.2.0a-Source.zip|acsegmentor-0.2.0a-Source.zip]]
January 18, 2009, at 06:08 PM by 81.240.213.170 -
Changed line 18 from:
* '''Version 0.2a''' (18 Janvier 2008)
to:
* '''Version 0.2a''' (18 January 2009)
January 18, 2009, at 06:07 PM by 81.240.213.170 -
Changed line 19 from:
** '''NEWS'''
to:
** '''Changes'''
January 18, 2009, at 06:07 PM by 81.240.213.170 -
Added lines 19-22:
** '''NEWS'''
*** GUI improvements.
*** Better default parameters.
*** Compilation fixes for newer gcc (v4.3.2).
January 18, 2009, at 06:03 PM by 81.240.213.170 -
Changed lines 14-15 from:
More details can be found in this '''draft paper''' [[{$PubDirUrl}/files/research/burrus.07.pr.segmentation_draft.pdf | PDF]] submitted to Pattern Recognition or in this paper (in french) presented to RFIA 2008 [[{$PubDirUrl}/files/research/burrus.08.rfia.segmentation.pdf | PDF]].
to:
More details can be found in this '''paper''' [[{$PubDirUrl}/files/research/burrus.09.pr.segmentation.pdf | PDF]] to appear in Pattern Recognition or in this paper (in french) presented to RFIA 2008 [[{$PubDirUrl}/files/research/burrus.08.rfia.segmentation.pdf | PDF]].
Changed lines 18-20 from:

* '''Version 0.1''' (14 September 2007)
** Source [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Source.tar.bz2|acsegmentor-0.1.0-Source.tar.bz2]] or [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Source.zip|acsegmentor-0.1.0-Source.zip]] (bigger)
to:
* '''Version 0.2a''' (18 Janvier 2008)
** Source [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.2.0a-Source.tar.bz2|acsegmentor-0.2.0a-Source.tar.bz2]] or [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.2.0a-Source.zip|acsegmentor-0.2.0a-Source.zip]] (bigger)
Added lines 21-27:
*** amd64: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.2.0a-Linux-amd64.tar.bz2|acsegmentor-0.2.0a-Linux-amd64.tar.bz2]]
** '''Other platforms'''
*** No binaries yet. Compilation has not yet been tested on Windows neither Mac OS X.

* '''Version 0.1''' (14 September 2007)
** Source [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Source.tar.bz2|acsegmentor-0.1.0-Source.tar.bz2]] or [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Source.zip|acsegmentor-0.1.0-Source.zip]] (bigger)
** '''Linux''' binaries
January 18, 2009, at 01:48 PM by 81.240.213.170 -
Changed lines 69-74 from:
     exploration heuristic and watershed initialization with sigma=0.8

  $ acsegmentor
--image lena.pgm --output myoutput.pgm --initializer egbis
  => idem as above with an egbis initialization with default parameters
    (k=300, sigma=0.8), result is in `myoutput.pgm'
to:
     exploration heuristic and egbis initialization with sigma=0.8 K=150 minsize=20

  $ acsegmentor
--image lena.pgm --output myoutput.pgm --initializer watershed
  => idem as above with a watershed initialization with default parameters
    (sigma=0.8), result is in `myoutput.pgm'
Changed lines 95-96 from:
  $ acsegmentor --threshold-database-output thresholds.xml \
                --width 1024 --height 1024 --initializer egbis \
to:
  $ acsegmentor --learn --threshold-database thresholds.xml \
                --width 1024 --height 1024 \
Changed lines 14-15 from:
More details can be found in this '''draft paper''' [[{$PubDirUrl}/files/research/burrus.07.pr.segmentation_draft.pdf | PDF]] submitted to Pattern Recognition.
to:
More details can be found in this '''draft paper''' [[{$PubDirUrl}/files/research/burrus.07.pr.segmentation_draft.pdf | PDF]] submitted to Pattern Recognition or in this paper (in french) presented to RFIA 2008 [[{$PubDirUrl}/files/research/burrus.08.rfia.segmentation.pdf | PDF]].
Changed lines 1-2 from:
(:title ''A contrario'' segmentor: Acsegmentor:)
to:
(:title ''A contrario'' segmentation: Acsegmentor:)
Changed lines 1-2 from:
(:title A contrario segmentor: Acsegmentor:)
to:
(:title ''A contrario'' segmentor: Acsegmentor:)
Changed lines 1-2 from:
(:title A contrario segmentor:)
to:
(:title A contrario segmentor: Acsegmentor:)
Added lines 1-2:
(:title A contrario segmentor:)
Changed lines 4-5 from:
Contact: mailto:burrus@ensta.fr
to:
Contact: mailto:Nicolas.Burrus@ensta.fr
Changed line 23 from:
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Darwin.tar.bz2|acsegmentor-0.1.0-Darwin.tar.bz2]]
to:
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Darwin.zip|acsegmentor-0.1.0-Darwin.zip]]
Changed line 23 from:
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-MacOSX-intel.tar.bz2|acsegmentor-0.1.0-Darwin.tar.bz2]]
to:
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Darwin.tar.bz2|acsegmentor-0.1.0-Darwin.tar.bz2]]
Changed line 23 from:
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-MacOSX-intel.tar.bz2|acsegmentor-0.1.0-MacOSX11-intel.tar.bz2]]
to:
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-MacOSX-intel.tar.bz2|acsegmentor-0.1.0-Darwin.tar.bz2]]
Changed line 118 from:
<td>{$PubDirUrl}/files/research/acsegmentor/house-egbis-filtered.png Filtered (9 regions)</td>
to:
<td>{$PubDirUrl}/files/research/acsegmentor/noise-egbis-filtered.png Filtered (9 regions)</td>
Changed lines 107-108 from:
<td>{$PubDirUrl}/files/research/acsegmentor/house-watershed.png Watershed (xx regions)</td>
<td>{$PubDirUrl}/files/research/acsegmentor/house-watershed-filtered.png Filtered (xx regions)</td>
to:
<td>{$PubDirUrl}/files/research/acsegmentor/house-watershed.png Watershed (1839 regions)</td>
<td>{$PubDirUrl}/files/research/acsegmentor/house-watershed-filtered.png Filtered (54 regions)</td>
Changed lines 110-111 from:
<tr align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
<td>{$PubDirUrl}/files/research/acsegmentor/house-egbis-filtered.png Filtered (xx regions)</td>
to:
<tr align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (267 regions)</td>
<td>{$PubDirUrl}/files/research/acsegmentor/house-egbis-filtered.png Filtered (36 regions)</td>
Added lines 114-120:

<table class="wikitable" width="100%">
<tr align="center"><td>{$PubDirUrl}/files/research/acsegmentor/noise.png "House" image</td>
<td>{$PubDirUrl}/files/research/acsegmentor/noise-egbis.png Egbis (1867 regions)</td>
<td>{$PubDirUrl}/files/research/acsegmentor/house-egbis-filtered.png Filtered (9 regions)</td>
</tr>
</table>
Changed line 21 from:
*** amd64: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Linux-x86.tar.bz2|acsegmentor-0.1.0-Linux-amd64.tar.bz2]]
to:
*** amd64: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Linux-amd64.tar.bz2|acsegmentor-0.1.0-Linux-amd64.tar.bz2]]
Changed line 18 from:
** Source [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Source.tar.bz2|acsegmentor-0.1-Source.tar.bz2]] or [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Source.zip|acsegmentor-0.1-Source.zip]] (bigger)
to:
** Source [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Source.tar.bz2|acsegmentor-0.1.0-Source.tar.bz2]] or [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Source.zip|acsegmentor-0.1.0-Source.zip]] (bigger)
Changed lines 20-21 from:
*** x86: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Linux-x86.tar.bz2|acsegmentor-0.1-Linux-x86.tar.bz2]]
*** amd64: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Linux-x86.tar.bz2|acsegmentor-0.1-Linux-amd64.tar.bz2]]
to:
*** x86: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Linux-x86.tar.bz2|acsegmentor-0.1.0-Linux-x86.tar.bz2]]
*** amd64: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Linux-x86.tar.bz2|acsegmentor-0.1.0-Linux-amd64.tar.bz2]]
Changed lines 23-25 from:
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-MacOSX-intel.tar.bz2|acsegmentor-0.1-MacOSX11-intel.tar.bz2]]
** '''Windows''' binaries (32bits, tested with VC8 and mingw with `WinXP): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Windows.zip|acsegmentor-0.1-Windows.zip]]
to:
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-MacOSX-intel.tar.bz2|acsegmentor-0.1.0-MacOSX11-intel.tar.bz2]]
** '''Windows''' binaries (32bits, tested with VC8 and mingw with `WinXP): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.0-Windows.zip|acsegmentor-0.1.0-Windows.zip]]
Changed line 23 from:
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-MacOSX11-intel.tar.bz2|acsegmentor-0.1-MacOSX11-intel.tar.bz2]]
to:
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-MacOSX-intel.tar.bz2|acsegmentor-0.1-MacOSX11-intel.tar.bz2]]
Changed lines 20-21 from:
*** x86 [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Linux-x86.tar.bz2|acsegmentor-0.1-Linux-x86.tar.bz2]]
*** amd64 [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Linux-x86.tar.bz2|acsegmentor-0.1-Linux-amd64.tar.bz2]]
to:
*** x86: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Linux-x86.tar.bz2|acsegmentor-0.1-Linux-x86.tar.bz2]]
*** amd64: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Linux-x86.tar.bz2|acsegmentor-0.1-Linux-amd64.tar.bz2]]
Changed lines 23-25 from:
*** Intel (tested on Tiger 10.4.10) [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-MacOSX11-intel.tar.bz2|acsegmentor-0.1-MacOSX11-intel.tar.bz2]]
** '''Windows''' binaries (32bits, tested with VC8 and mingw in WinXP) [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Windows.zip|acsegmentor-0.1-Windows.zip]]
to:
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-MacOSX11-intel.tar.bz2|acsegmentor-0.1-MacOSX11-intel.tar.bz2]]
** '''Windows''' binaries (32bits, tested with VC8 and mingw with `WinXP): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Windows.zip|acsegmentor-0.1-Windows.zip]]
Changed lines 20-21 from:
*** x86: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Linux-x86.tar.bz2|acsegmentor-0.1-Linux-x86.tar.bz2]]
*** amd64: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Linux-x86.tar.bz2|acsegmentor-0.1-Linux-amd64.tar.bz2]]
to:
*** x86 [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Linux-x86.tar.bz2|acsegmentor-0.1-Linux-x86.tar.bz2]]
*** amd64 [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Linux-x86.tar.bz2|acsegmentor-0.1-Linux-amd64.tar.bz2]]
Changed lines 23-25 from:
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-MacOSX11-intel.tar.bz2|acsegmentor-0.1-MacOSX11-intel.tar.bz2]]
** '''Windows''' binaries (32bits, tested with VC8 and mingw in WinXP)[[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Windows.zip|acsegmentor-0.1-Windows.zip]]
to:
*** Intel (tested on Tiger 10.4.10) [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-MacOSX11-intel.tar.bz2|acsegmentor-0.1-MacOSX11-intel.tar.bz2]]
** '''Windows''' binaries (32bits, tested with VC8 and mingw in WinXP) [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Windows.zip|acsegmentor-0.1-Windows.zip]]
Changed line 22 from:
** '''`MacOSX''' binaries
to:
** '''Mac OS X''' binaries
Changed line 22 from:
** `'''MacOSX''' binaries
to:
** '''`MacOSX''' binaries
Changed line 19 from:
** Linux binaries
to:
** '''Linux''' binaries
Changed lines 22-25 from:
** `MacOSX binaries
*** Intel: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-MacOSX11-intel.tar.bz2|acsegmentor-0.1-MacOSX11-intel.tar.bz2]]
** Windows binaries, run it with [@command.com@] or [[http://www.mingw.org/msys.shtml|Msys]] to provide command line arguments: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Windows.zip|acsegmentor-0.1-Windows.zip]]
to:
** `'''MacOSX''' binaries
*** Intel (tested on Tiger 10.4.10): [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-MacOSX11-intel.tar.bz2|acsegmentor-0.1-MacOSX11-intel.tar.bz2]]
** '''Windows''' binaries (32bits, tested with VC8 and mingw in WinXP)[[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Windows.zip|acsegmentor-0.1-Windows.zip]]
Changed line 17 from:
* '''Version 0.1''' (5 September 2007)
to:
* '''Version 0.1''' (14 September 2007)
Deleted line 17:
** '''Note:''' The code still has a "research flavor", i.e. suffer from incremental development design issues.
Changed lines 12-13 from:
More details can be found in this ***draft paper*** [[{$PubDirUrl}/files/research/burrus.07.pr.segmentation_draft.pdf | PDF]] submitted to Pattern Recognition.
to:
More details can be found in this '''draft paper''' [[{$PubDirUrl}/files/research/burrus.07.pr.segmentation_draft.pdf | PDF]] submitted to Pattern Recognition.
Changed lines 12-13 from:
More details can be found in this draft [[{$PubDirUrl}/files/research/burrus.07.pr.segmentation_draft.pdf | PDF]] submitted to Pattern Recognition.
to:
More details can be found in this ***draft paper*** [[{$PubDirUrl}/files/research/burrus.07.pr.segmentation_draft.pdf | PDF]] submitted to Pattern Recognition.
Changed lines 60-62 from:
for the GUI version, or type [@acsegmentor --help@] to find the (numerous) available
command
line options.
to:
   for the GUI version, or type [@acsegmentor --help@] to find the (numerous) available
 
command line options.
Changed lines 31-32 from:
Acsegmentor uses CMake (http://www.cmake.org) to generate Makefiles, `KDevelop, `XCode or `VisualStudio projects. Once cmake is installed, you just need to run it on the root directory of the source tree.  It is available in most Linux distributions.
to:
Acsegmentor uses `CMake (http://www.cmake.org) to generate Makefiles, `KDevelop, `XCode or `VisualStudio projects. Once cmake is installed, you just need to run it on the root directory of the source tree.  It is available in most Linux distributions.
Changed line 24 from:
*** Intel and X11: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-MacOSX11-intel.tar.bz2|acsegmentor-0.1-MacOSX11-intel.tar.bz2]]
to:
*** Intel: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-MacOSX11-intel.tar.bz2|acsegmentor-0.1-MacOSX11-intel.tar.bz2]]
Changed lines 59-61 from:
** Acsegmentor aims at segmenting an image into homogenenous regions.
** Use [@acsegmentor --help@] to find the (numerous) available command line options
to:
** There are a console mode and a GUI mode. Use it without command line parameters
for the GUI version, or type [@acsegmentor --help@] to find the (numerous) available
command line
options.
Changed line 65 from:
  $ acsegmentor --image lena.pgm --output output.pgm
to:
  $ acsegmentor --image lena.pgm
Changed line 70 from:
  $ acsegmentor --image lena.pgm --output output.pgm --initializer egbis
to:
  $ acsegmentor --image lena.pgm --output myoutput.pgm --initializer egbis
Changed lines 72-74 from:
     (k=50, sigma=0.8).

  $ acsegmentor --image bigimage
.pgm --output output.pgm
to:
     (k=300, sigma=0.8), result is in `myoutput.pgm'

  $ acsegmentor --image bigimage.pgm
Changed lines 76-79 from:
  => Thresholds were pre-computed for some standard image sizes
     256x256, 384x256 and 512x512. For other sizes, you have to
     learn new thresholds (see LEARNING EXAMPLES).
to:
  => Thresholds were pre-computed for some 256x256 images.
    For other sizes, you have to learn new thresholds
 
  (see LEARNING EXAMPLES).
Changed line 98 from:
  => 1000 images will be analyzed to deduce statistical thresholds.
to:
  => 1000 noise images will be analyzed to deduce statistical thresholds.
Added line 18:
** '''Note:''' The code still has a "research flavor", i.e. suffer from incremental development design issues.
Changed lines 59-60 from:
** Use `acsegmentor --help' to find the (numerous) available command line options
to:
** Use [@acsegmentor --help@] to find the (numerous) available command line options
Changed line 17 from:
* '''Version 0.1'''
to:
* '''Version 0.1''' (5 September 2007)
Changed lines 30-31 from:
Acsegmentor uses CMake (http://www.cmake.org) to generate Makefiles, KDevelop, XCode or VisualStudio projects. Once cmake is installed, you just need to run it on the root directory of the source tree.  It is available in most Linux distributions.
to:
Acsegmentor uses CMake (http://www.cmake.org) to generate Makefiles, `KDevelop, `XCode or `VisualStudio projects. Once cmake is installed, you just need to run it on the root directory of the source tree.  It is available in most Linux distributions.
Changed line 22 from:
** MacOSX binaries
to:
** `MacOSX binaries
Changed lines 24-25 from:
** Windows binaries, run it with [@command.com@] or [[http://www.mingw.org/msys.shtml|Msys]] to provide command line arguments: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.exe|acsegmentor-0.1.exe]]
to:
** Windows binaries, run it with [@command.com@] or [[http://www.mingw.org/msys.shtml|Msys]] to provide command line arguments: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Windows.zip|acsegmentor-0.1-Windows.zip]]
Added lines 17-25:
* '''Version 0.1'''
** Source [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Source.tar.bz2|acsegmentor-0.1-Source.tar.bz2]] or [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Source.zip|acsegmentor-0.1-Source.zip]] (bigger)
** Linux binaries
*** x86: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Linux-x86.tar.bz2|acsegmentor-0.1-Linux-x86.tar.bz2]]
*** amd64: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-Linux-x86.tar.bz2|acsegmentor-0.1-Linux-amd64.tar.bz2]]
** MacOSX binaries
*** Intel and X11: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1-MacOSX11-intel.tar.bz2|acsegmentor-0.1-MacOSX11-intel.tar.bz2]]
** Windows binaries, run it with [@command.com@] or [[http://www.mingw.org/msys.shtml|Msys]] to provide command line arguments: [[{$PubDirUrl}/files/research/acsegmentor/acsegmentor-0.1.exe|acsegmentor-0.1.exe]]

Changed lines 4-5 from:
'''Contact:''' mailto:burrus@ensta.fr
to:
Contact: mailto:burrus@ensta.fr
Added line 16:
Changed lines 3-4 from:
Contact: mailto:burrus@ensta.fr
to:

'''
Contact:''' mailto:burrus@ensta.fr
Changed lines 3-4 from:
to:
Contact: mailto:burrus@ensta.fr
Added line 45:
Deleted lines 11-23:
!! Examples


<table class="wikitable" width="100%">
<tr align="center"><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
<td>{$PubDirUrl}/files/research/acsegmentor/house-watershed.png Watershed (xx regions)</td>
<td>{$PubDirUrl}/files/research/acsegmentor/house-watershed-filtered.png Filtered (xx regions)</td>
</tr>
<tr align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
<td>{$PubDirUrl}/files/research/acsegmentor/house-egbis-filtered.png Filtered (xx regions)</td>
</tr>
</table>

Added lines 43-99:

* Introduction
** Acsegmentor aims at segmenting an image into homogenenous regions.
** Use `acsegmentor --help' to find the (numerous) available command line options

* Segmentation examples
[@
  $ acsegmentor --image lena.pgm --output output.pgm
  => segment the image lena, resulting segmentation is in `output.pgm'.
  => use default parameters: a contrario segmentation with MergeBest
    exploration heuristic and watershed initialization with sigma=0.8

  $ acsegmentor --image lena.pgm --output output.pgm --initializer egbis
  => idem as above with an egbis initialization with default parameters
    (k=50, sigma=0.8).

  $ acsegmentor --image bigimage.pgm --output output.pgm
  => Exception raised because no thresholds can be found.
  => Thresholds were pre-computed for some standard image sizes
    256x256, 384x256 and 512x512. For other sizes, you have to
    learn new thresholds (see LEARNING EXAMPLES).

  $ acsegmentor --image bigimage.pgm --output output.pgm --sigma 1.1
  => Exception raised because no thresholds can be found.
  => Specific thresholds must be computed for each parameter.
    Pre-computed thresholds are given only for default parameters.
  => You have to run a learning process.

  $ acsegmentor --image bigimage.pgm --output output.pgm \
                --threshold-database thresholds.xml
  => Read additional thresholds from `thresholds.xml'. These
    thresholds can be generated automatically by the learning phase.
@]

* Learning examples
[@
  $ acsegmentor --threshold-database-output thresholds.xml \
                --width 1024 --height 1024 --initializer egbis \
                --nb-iterations 1000
  => Learn thresholds for 1024x1024 images for an egbis initializer.
  => 1000 images will be analyzed to deduce statistical thresholds.
  => Resulting thresholds will be put into `thresholds.xml'. This file
    can then be used to segment new 1024x1024 images.
@]

!! Examples


<table class="wikitable" width="100%">
<tr align="center"><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
<td>{$PubDirUrl}/files/research/acsegmentor/house-watershed.png Watershed (xx regions)</td>
<td>{$PubDirUrl}/files/research/acsegmentor/house-watershed-filtered.png Filtered (xx regions)</td>
</tr>
<tr align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
<td>{$PubDirUrl}/files/research/acsegmentor/house-egbis-filtered.png Filtered (xx regions)</td>
</tr>
</table>
Added line 14:
Changed lines 16-17 from:
   <td>{$PubDirUrl}/files/research/acsegmentor/house-watershed.png Watershed (xx regions)</td>
   <td>{$PubDirUrl}/files/research/acsegmentor/house-watershed-filtered.png Filtered (xx regions)</td>
to:
<td>{$PubDirUrl}/files/research/acsegmentor/house-watershed.png Watershed (xx regions)</td>
<td>{$PubDirUrl}/files/research/acsegmentor/house-watershed-filtered.png Filtered (xx regions)</td>
Changed line 20 from:
   <td>{$PubDirUrl}/files/research/acsegmentor/house-egbis-filtered.png Filtered (xx regions)</td>
to:
<td>{$PubDirUrl}/files/research/acsegmentor/house-egbis-filtered.png Filtered (xx regions)</td>
Added line 13:
Deleted line 12:
Changed line 15 from:
<tr style="border-style:'hidden'" align="center"><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
to:
<tr align="center"><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
Changed line 19 from:
<tr style="border-style:'hidden'" align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
to:
<tr align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
Changed line 15 from:
<tr border-style="hidden" align="center"><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
to:
<tr style="border-style:'hidden'" align="center"><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
Changed line 19 from:
<tr border-style="hidden" align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
to:
<tr style="border-style:'hidden'" align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
Changed line 15 from:
<tr border-style="none" align="center"><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
to:
<tr border-style="hidden" align="center"><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
Changed line 19 from:
<tr border-style="none" align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
to:
<tr border-style="hidden" align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
Changed line 15 from:
<tr border=0 align="center"><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
to:
<tr border-style="none" align="center"><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
Changed line 19 from:
<tr border=0 align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
to:
<tr border-style="none" align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
Changed lines 8-11 from:
Two algorithms are implemented to provide to initial partitions: classical watershed (Vincent & Soille) and the algorithm of P. Felzenszwalb and D. Huttenlocher published in the IJCV paper "Efficient Graph-Based Image Segmentation" ([[http://people.cs.uchicago.edu/~pff/segment/|authors' webpage]]), called EGBIS here.

More details can be found in this draft [[{$PubDirUrl/files/research/burrus.07.pr.segmentation_draft.pdf} | PDF]] submitted to Pattern Recognition.
to:
Two algorithms are implemented to provide to initial partitions: classical watershed (Vincent & Soille) and the algorithm of P. Felzenszwalb and D. Huttenlocher published in the IJCV paper "Efficient Graph-Based Image Segmentation" ([[http://people.cs.uchicago.edu/~pff/segment/|authors' webpage]]), called '''EGBIS''' here.

More details can be found in this draft [[{$PubDirUrl}/files/research/burrus.07.pr.segmentation_draft.pdf | PDF]] submitted to Pattern Recognition.
Changed lines 8-9 from:
Two algorithms are implemented to provide to initial partitions: classical watershed (Vincent & Soille) and the algorithm of P. Felzenszwalb and D. Huttenlocher published in the IJCV paper "Efficient Graph-Based Image Segmentation" ([[http://people.cs.uchicago.edu/~pff/segment/|Authors' webpage]]).
to:
Two algorithms are implemented to provide to initial partitions: classical watershed (Vincent & Soille) and the algorithm of P. Felzenszwalb and D. Huttenlocher published in the IJCV paper "Efficient Graph-Based Image Segmentation" ([[http://people.cs.uchicago.edu/~pff/segment/|authors' webpage]]), called EGBIS here.
Changed lines 8-9 from:
Two algorithms are implemented to provide to initial partitions: classical watershed (Vincent & Soille) and the algorithm of P. Felzenszwalb and D. Huttenlocher published in the IJCV paper "Efficient Graph-Based Image Segmentation" ([[http://people.cs.uchicago.edu/~pff/segment/|Web page of the authors]).
to:
Two algorithms are implemented to provide to initial partitions: classical watershed (Vincent & Soille) and the algorithm of P. Felzenszwalb and D. Huttenlocher published in the IJCV paper "Efficient Graph-Based Image Segmentation" ([[http://people.cs.uchicago.edu/~pff/segment/|Authors' webpage]]).
Changed lines 6-7 from:
Acsegmentor comes with an example of distance function which analyze gray level distributions difference, deviations and frontier contrast between couples of regions. It also comes with a simple exploration heuristic, which, starting with a initial partition, iteratively merges the least different regions until only meaningful couples of regions remain.
to:
Acsegmentor comes with an example of distance function which analyzes frontier contrast, gray level distributions and deviations differences between couples of regions. It also comes with a simple exploration heuristic, which, starting with a initial partition, iteratively merges the least different regions until only meaningful couples of regions remain.

Two algorithms are implemented to provide to initial partitions: classical watershed (Vincent & Soille) and the algorithm of P. Felzenszwalb and D. Huttenlocher published in the IJCV paper "Efficient Graph-Based Image Segmentation" ([[http://people.cs.uchicago.edu/~pff/segment/|Web page of the authors])
.
Changed lines 4-5 from:
Acsegmentor aims at segmenting gray-level images into homogeneous regions. It's a generic algorithm: it requires a distance function between regions, an exploration heuristic and automatically find thresholds ensuring that regions in the final partitions will be statistically meaningfully different. This step is done using ''a contrario'' reasoning: two regions are meaningfully different is the probability that the exploration heuristic find such different regions in pure noise is very low. This ensures that in the final partition, statistically, regions difference are not due to chance but are a result of some physical phenomena, such as different objects in the scene.
to:
Acsegmentor aims at segmenting gray-level images into homogeneous regions. It's a generic algorithm: it requires a distance function between regions, an exploration heuristic and automatically find thresholds ensuring that regions in the final partitions will be statistically meaningfully different. This step is done using '''''a contrario''''' reasoning: two regions are meaningfully different is the probability that the exploration heuristic find such different regions in pure noise is very low. This ensures that in the final partition, statistically, regions difference are not due to chance but are a result of some physical phenomena, such as different objects in the scene.
Changed line 17 from:
<tr align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
to:
<tr border=0 align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
Changed line 13 from:
<tr><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
to:
<tr border=0 align="center"><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
Changed line 17 from:
<tr><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
to:
<tr align="center"><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
Changed line 15 from:
   <td>{$PubDirUrl}/files/research/acsegmentor/house-watershed-filtered.png" Filtered (xx regions)</td>
to:
   <td>{$PubDirUrl}/files/research/acsegmentor/house-watershed-filtered.png Filtered (xx regions)</td>
Changed lines 13-15 from:
<tr><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png</td>
    <td>{$PubDirUrl}/files/research/acsegmentor/house-watershed.png</td>
 
   <td>{$PubDirUrl}/files/research/acsegmentor/house-watershed-filtered.png</td>
to:
<tr><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png "House" image</td>
   <td>{$PubDirUrl}/files/research/acsegmentor/house-watershed.png Watershed (xx regions)</td>
   <td>{$PubDirUrl}/files/research/acsegmentor/house-watershed-filtered.png" Filtered (xx regions)</td>
Changed lines 17-18 from:
<tr><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png</td>
 
   <td>{$PubDirUrl}/files/research/acsegmentor/house-egbis-filtered.png</td>
to:
<tr><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png Egbis (xx regions)</td>
   <td>{$PubDirUrl}/files/research/acsegmentor/house-egbis-filtered.png Filtered (xx regions)</td>
Changed line 12 from:
<table class="wikitable">
to:
<table class="wikitable" width="100%">
Added lines 12-21:
<table class="wikitable">
<tr><td rowspan=2>{$PubDirUrl}/files/research/acsegmentor/house.png</td>
    <td>{$PubDirUrl}/files/research/acsegmentor/house-watershed.png</td>
    <td>{$PubDirUrl}/files/research/acsegmentor/house-watershed-filtered.png</td>
</tr>
<tr><td>{$PubDirUrl}/files/research/acsegmentor/house-egbis.png</td>
    <td>{$PubDirUrl}/files/research/acsegmentor/house-egbis-filtered.png</td>
</tr>
</table>

Changed lines 18-22 from:
Acsegmentor uses CMake (http://www.cmake.org) to generate Makefiles,
KDevelop, XCode or VisualStudio projects.
Once cmake is installed, you just need to run it on the root directory
of the source tree.  It is available in most Linux distributions.
to:
Acsegmentor uses CMake (http://www.cmake.org) to generate Makefiles, KDevelop, XCode or VisualStudio projects. Once cmake is installed, you just need to run it on the root directory of the source tree.  It is available in most Linux distributions.
Changed lines 21-25 from:
Acsegmentor also depends upon VXL (http://vxl.sourceforge.net), Boost
(http://boost.org) and Juce (http://www.rawmaterialsoftware.com/juce/).
These libraries are embedded in the source tree to avoid extra
installations and to make sure that you have a compatible version.
to:
Acsegmentor also depends upon VXL (http://vxl.sourceforge.net), Boost (http://boost.org) and Juce (http://www.rawmaterialsoftware.com/juce/). These libraries are embedded in the source tree to avoid extra installations and to make sure that you have a compatible version.
Changed line 17 from:
* `CMake
to:
* '''`CMake''' \\
Changed line 23 from:
* Dependencies
to:
* '''Dependencies''' \\
Changed line 29 from:
* Example on Unix
to:
* '''Example on Unix''' \\
Changed line 17 from:
* CMake
to:
* `CMake
Deleted line 29:
Changed lines 17-18 from:
!!! Requirements
to:
* CMake
Deleted line 19:
Added line 23:
* Dependencies
Deleted line 25:
Changed lines 29-30 from:
!!! Example on Unix
to:
* Example on Unix
Added line 3:
Added lines 16-50:

!!! Requirements

Acsegmentor uses CMake (http://www.cmake.org) to generate Makefiles,
KDevelop, XCode or VisualStudio projects.

Once cmake is installed, you just need to run it on the root directory
of the source tree.  It is available in most Linux distributions.

Acsegmentor also depends upon VXL (http://vxl.sourceforge.net), Boost
(http://boost.org) and Juce (http://www.rawmaterialsoftware.com/juce/).

These libraries are embedded in the source tree to avoid extra
installations and to make sure that you have a compatible version.

!!! Example on Unix

[@
$ mkdir build
$ cd build
$ ccmake /path/to/acsegmentor-0.1-Source
=> Console based-interface
=> Type 'c' (configure, maybe twice)
  and then 'g' (generate) to create Makefiles.
=> You might want to change build settings. For example, to enable
  both optimizations and debugging symbols,
  enter `RelWithDebInfo' in CMAKE_BUILD_TYPE. For the fastest binaries,
  enter `Release'.

$ make

$ src/acsegmentor
=> should be ok
@]

Added lines 3-8:
Acsegmentor aims at segmenting gray-level images into homogeneous regions. It's a generic algorithm: it requires a distance function between regions, an exploration heuristic and automatically find thresholds ensuring that regions in the final partitions will be statistically meaningfully different. This step is done using ''a contrario'' reasoning: two regions are meaningfully different is the probability that the exploration heuristic find such different regions in pure noise is very low. This ensures that in the final partition, statistically, regions difference are not due to chance but are a result of some physical phenomena, such as different objects in the scene.

Acsegmentor comes with an example of distance function which analyze gray level distributions difference, deviations and frontier contrast between couples of regions. It also comes with a simple exploration heuristic, which, starting with a initial partition, iteratively merges the least different regions until only meaningful couples of regions remain.

More details can be found in this draft [[{$PubDirUrl/files/research/burrus.07.pr.segmentation_draft.pdf} | PDF]] submitted to Pattern Recognition.

Changed lines 1-2 from:
!! Project description
to:
!! Introduction
Added lines 1-9:
!! Project description

!! Examples

!! Download

!! Installation

!! Basic usage