
Alexandre Abraham.
Topological Watershed.
CSI Seminar 0835 EPITA 25/06/08
Dividing a picture into area of interest is called picture segmentation, it is useful in particular to point out cancerous cells in medical imaging. The Watershed Transform provides such a segmentation and can be implemented in many ways. Here we will focus on the Topological Watershed, an efficient algorithm producing results with nice properties. In this report, we will show how this algorithm has been implemented in Milena, the C++ generic image processing library of the Olena platform, developed at LRDE. We will first see how to handle usual image format and then generalize to trickier formats like pictures mapped on general graphs.
to top