0

I have implemented the marker-less (so not like OpenCV) watershed algorithm proposed in a 1991 paper by Vincent and Soille. I have also implemented a distance transform algorithm to apply it before watersheding.

It works well in a good number of cases, but sometimes it produces a little oversegmentation. I also corrected some of this with gauss filtering the distance-transform image.

I am planning to correct this by applying thresholding to the watersheds. Therefore considering watershed of only some height greater than a threshold

Considering that this paper is quite old (1991) I am wondering if anyone knows of papers or resources that explain something similar to what I intend to do.

Notes:

1) I am not using OpenCV. I am implementing all by myself from papers

2) I am going for a marker-less watersheding.

KansaiRobot
  • 7,564
  • 11
  • 71
  • 150
  • What specifically is your question? Are you looking for other (more modern) papers on this technique? Perhaps you could upload an example of the issues you're having? – Mozglubov Oct 18 '17 at 02:34
  • @Mozglubov There are several approaches to watershedding. OpenCV for example uses markers. I implemented one without markers based on that paper. My question is if there have been improvements in the algorithm of that paper – KansaiRobot Oct 26 '17 at 04:25
  • The issue I am having is the one posted here https://stackoverflow.com/questions/46107628/problems-with-segmenting-pills – KansaiRobot Oct 26 '17 at 04:26

0 Answers0