This is an example project, showcasing how you can use the surface tension of the ‘pixel-based object resizing’ algorithm to generalize your image objects.


Surface tension:
You can define surface tension per object or per class. A defined box is then drawn for every pixel and the entered operation and value represent to coverage of the object/class. If the surface tension condition is fulfilled the object will then grow or shrink, if not, nothing is executed.

pixel-based_object_resizing_surface_tension.gif

The basis of the loaded project is an artificial image with the red area having an extrusion in the upper part and a intrusion in the lower part. You will learn how to fill the intrusion using the algorithm ‘pixel-based object resizing’ with mode ‘growing’ and a ‘Candidate surface tension’ set and also how extrusion can be cut also using the algorithm ‘pixel-based object resizing’ but with the mode 'shrinking'.

 

Fill an intrusion with growing and surface tension

To fill an intrusion you can use the algorithm ‘pixel-based object resizing’ together with the surface tension condition, which can be set in the Parameters section of this algorithm.
To fill an intrusion the red class ‘A’ has to grow in class ‘B’, but only if the surface tension is more than 0.5, respectively if the object covers the box with more than 50%.

Cut extrusion with shrinking and surface tension

In a second step the class ‘A’ is shrunken, but only if the surface tension is less than 0.5, respectively if the box is covered with less than 0.5 by the object. In opposite to the growing procedure a larger box size is used. If the box size is too small, the extrusion will not completely be removed.

Download 'Example Project - Pixel-Based Object Resizing Surface Tension Artificial'

 

Interesting related content:

0 comments

Your Answer

Articles in this section

Need more help?

Enter Community Contact Support