File: HooverCompareSegmentation.html

package info (click to toggle)

qgis 2.4.0-1

links: PTS, VCS
area: main
in suites: jessie, jessie-kfreebsd
size: 374,696 kB
ctags: 66,263
sloc: cpp: 396,139; ansic: 241,070; python: 130,609; xml: 14,884; perl: 1,290; sh: 1,287; sql: 500; yacc: 268; lex: 242; makefile: 168

file content (7 lines) | stat: -rw-r--r-- 3,046 bytes

<html><head>
<style type="text/css">
dl { border: 3px double #ccc; padding: 0.5em; } dt { float: left; clear: left; text-align: left; font-weight: bold; color: green; } dt:after { content: ":"; } dd { margin: 0 0 0 220px; padding: 0 0 0.5em 0; }
</style>
</head><body><h1>HooverCompareSegmentation</h1><h2>Brief Description</h2>Compare two segmentations with Hoover metrics<h2>Tags</h2>Segmentation<h2>Long Description</h2>This application compares a machine segmentation (MS) with a partial ground truth segmentation (GT). The Hoover metrics are used to estimate scores for correct detection, over-segmentation, under-segmentation and missed detection.
 The application can output the overall Hoover scores along with coloredimages of the MS and GT segmentation showing the state of each region (correct detection, over-segmentation, under-segmentation, missed)
 The Hoover metrics are described in : Hoover et al., "An experimental comparison of range image segmentation algorithms", IEEE PAMI vol. 18, no. 7, July 1996.<h2>Parameters</h2><ul><li><b>[param] -ingt</b> &lt;string&gt; A partial ground truth segmentation image.. Mandatory: True. Default Value: &quot;&quot;</li><li><b>[param] -inms</b> &lt;string&gt; A machine segmentation image.. Mandatory: True. Default Value: &quot;&quot;</li><li><b>[param] -bg</b> &lt;int32&gt; Label value of the background in the input segmentations. Mandatory: True. Default Value: &quot;0&quot;</li><li><b>[param] -th</b> &lt;float&gt; Overlapping threshold used to find Hoover instances.. Mandatory: True. Default Value: &quot;0.75&quot;</li><li><b>[param] -outgt</b> &lt;string&gt; The colored ground truth output image.. Mandatory: False. Default Value: &quot;&quot;</li><li><b>[param] -outms</b> &lt;string&gt; The colored machine segmentation output image.. Mandatory: False. Default Value: &quot;&quot;</li><li><b>[param] -rc</b> &lt;float&gt; Overall score for correct detection (RC). Mandatory: True. Default Value: &quot;0.0&quot;</li><li><b>[param] -rf</b> &lt;float&gt; Overall score for over segmentation (RF). Mandatory: True. Default Value: &quot;0.0&quot;</li><li><b>[param] -ra</b> &lt;float&gt; Overall score for under segmentation (RA). Mandatory: True. Default Value: &quot;0.0&quot;</li><li><b>[param] -rm</b> &lt;float&gt; Overall score for missed detection (RM). Mandatory: True. Default Value: &quot;0.0&quot;</li></ul><h2>Limitations</h2>None<h2>Authors</h2>OTB-Team<h2>See Also</h2>otbHooverMatrixFilter, otbHooverInstanceFilter, otbLabelMapToAttributeImageFilter<h2>Example of use</h2><ul><li><p style=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;">ingt: maur_GT.tif</p></li><li><p style=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;">inms: maur_labelled.tif</p></li><li><p style=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;">outgt: maur_colored_GT.tif uint8</p></li></ul></body></html>