mirror of
https://git.salome-platform.org/gitpub/modules/geom.git
synced 2024-12-26 17:30:35 +05:00
99 lines
2.4 KiB
Plaintext
99 lines
2.4 KiB
Plaintext
/*!
|
|
|
|
\page shape_recognition_page Shape recognition from a picture
|
|
|
|
\note
|
|
<ol>
|
|
<li>This functionality is not fully operational yet. It is provided for testing purpose and because it might already be helpful in some situations.
|
|
(Do not hesitate to make feedbacks on possible bugs ...) </li>
|
|
|
|
<li>The functionality is only available if SALOME has been built with the optional prerequisite OpenCV. </li>
|
|
</ol>
|
|
|
|
This tool allows you to automatically create geometrical shapes from
|
|
pictures with help of shape recognition algorithms.
|
|
<b>Contours</b> or <b>Corners</b> can be built.
|
|
|
|
\b Example:
|
|
|
|
Detection of the cost line on a nautical chart
|
|
|
|
\image html contour_detection_example2.png
|
|
|
|
\n
|
|
|
|
To use the <b>Shape recogition</b> tool:
|
|
|
|
<ol>
|
|
<li>\ref import_picture_page "Import a picture" in the view</li>
|
|
|
|
<li> Select <b>New Entity -> Shape Recognition</b> or click on \image html feature_detect.png </li>
|
|
|
|
</ol>
|
|
|
|
|
|
|
|
Then you can choose to create either <b>contours</b> or <b>corners</b> from this picture.
|
|
|
|
\n
|
|
|
|
To create <b>Contours</b> :
|
|
|
|
<ol>
|
|
<li> Select in the <b>Picture</b> field a previously imported picture.</li>
|
|
|
|
<li> Click on \image html occ_view_camera_dump.png </li>
|
|
|
|
<li> Draw a rectangle in the zone whose contour is to be found. The
|
|
zone will be identified by the colors of this <b>Filtering Sample</b>.
|
|
|
|
\b Example:
|
|
|
|
In the picture shown above, the contours have been drawn basing on
|
|
the sample, containing white and violet color, thus all white and
|
|
violet areas in the picture are included in the outlined zone.
|
|
|
|
\image html feature_detection_dlg3.png
|
|
|
|
|
|
|
|
<li> <b> Output type </b>
|
|
|
|
<ul>
|
|
|
|
<li> \b Spline : The \b result will be a \b Compound of \b Edges. Each contour will be a single \b edge based on a B-Spline curve (it will be smooth).</li>
|
|
|
|
<li> \b Polyline : The \b result will be a \b Compound of \b Wires. Each contour will be a wire made of lines (i.e. a \b Polygon)</li>
|
|
|
|
</ul>
|
|
|
|
In both cases each contour can then be retrieved by an explode operation with the appropriate subshape type.
|
|
|
|
</li>
|
|
|
|
\note It is better to use the \b Spline output type unless you want to find the frontier of a polygon (rectangle ...)
|
|
|
|
</ol>
|
|
|
|
|
|
\n
|
|
|
|
To create <b>Corners</b> :
|
|
|
|
<ol>
|
|
<li> In the <b>Picture</b> field select a previously imported picture.</li>
|
|
|
|
<li> Apply </li>
|
|
|
|
The \b Result will be a \b Compound of \b Vertices
|
|
|
|
\image html feature_detection_dlg2.png
|
|
|
|
|
|
|
|
</ol>
|
|
|
|
|
|
|
|
*/
|