Segmentation > *Auto Segmentation

Requires at least two B/W memory images

Uses geodesic-distance or marker-based watershed segmentation to auto-identify features based on two seed images. One seed image roughly identifies features and the other the background. Seed images can be any of the available B/W memory images.

1. Method

  • Geodesic Distance: Uses the geodesic distance method [1] to auto-determine feature boundaries the image based on the feature and background markers. Useful when only partial feature have been captured and the user needs the software to try to figure out the rest.
  • Marker-Based Watershed: First forces the image to have local minima at the feature and background marker locations. Then applies the watershed algorithm [2] to auto-determine feature boundaries. Tends to grow the existing feature boundaries about halfway to the background markers.

2. Features

Takes black features from a memory image and sets them to help identify features for auto segmentation

3. Background

Takes black features from a memory image and sets them to help identify the background for auto segmentation

References

[1] A. Protiere and G. Sapiro, Interactive Image Segmentation via Adaptive Weighted Distances, IEEE Transactions on Image Processing, Volume 16, Issue 4, 2007.

[2] Meyer, Fernand, “Topographic distance and watershed lines,” Signal Processing , Vol. 38, July 1994, pp. 113-125.

Need more help with this?
Chat with an expert now ››

Was this helpful?

Yes No
You indicated this topic was not helpful to you ...
Could you please leave a comment telling us why? Thank you!
Thanks for your feedback.