<<Prev 1 2 3 4 5 6 7 8
Videos
(862 KB) 22 seconds video of the original images moving over the conveyor.
(534 KB) 33 seconds video of the processed results of the parts (note that the video is slowed for viewing purposes).
Notice how the shapes will suddenly appear and disappear when approaching the border. This is the blob filter removing
objects whose shape may be altered by the image borders which may cause mismatches.
Pipeline
The following is the processing pipeline as seen within RoboRealm to accomplish the part processing.
Notes:
1. You will need to train the Shape_Match module on a folder that contains the database of
images to be matched. You can do this by downloading (.zip) all the images into a single folder (like c:\temp\Shape_Match), edit the
Shape_Match module, press the train button, change the path to your folder (e.g. c:\temp\Shape_Match) and press start.
2. You can view the final variables (like part orientation or COG) by adding in a Watch_Variables module or selecting
the appropriate checkbox in the Shape Matching module.
3. You can add in the firewire camera module or other modules to capture images. Or if you have a webcam connected just press
the "Camera" button for a live feed.
Your turn ...
Want to try this yourself? Following is the robofile that should launch RoboRealm with the original image
we used in this tutorial. You can click on each of the steps in the pipeline to review what the processing
looks like up to that point.
Download the Shape Matching robofile.
To use the video downloaded from the above .zip file configure the media reader module in this robofile to point to that video. Note that
you can slow the video speed down in the media reader to get a slower frame by frame view.
The End
That's all folks. We hope you've enjoyed this little adventure into an application of machine vision processing
and have inspired you to download a free trial of our software.
If you have any questions or comments about this tutorial please feel free to
contact us.
Have a nice day!
<<Prev 1 2 3 4 5 6 7 8
|