Computing Watersheds 2D

Computing watersheds can be a powerful technique for separating the overlapping objects in an image. This technique uses the labels of a multi-ROI as the seed points and a landscape image whose 'catchment basins' correspond to the objects you want to identify. In the example below, a watershed 2D was applied to segment the poppy seeds in a dataset.

From left to right: original dataset, ROI mask, distance map from ROI mask, multi-ROI seeds, computed segmentation

You should note that when you select Compute Watershed 2D, you will be prompted to select a region of interest. The ROI will be used to compute a distance map within which the watershed will be enclosed, as shown above.

You should first complete all of the required pre-processing steps before you attempt to apply a watershed 2D to your data. This can include creating a region of interest that will used to compute a distance map whose 'catchment basins' are the objects that you want to identify and creating a multi-ROI with the required seed points. Refer to the topics in Pre-Processing Steps for information about these steps.

1. Right-click the multi-ROI what will provide the seed points and then choose Compute Watershed 2D in the pop-up menu.

   Note Refer to the topic Seeds for information about creating multi-ROIs that will provide the seed points.

2. Choose the region of interest that will used to compute a distance map in the Choose the ROI to Compute a Distance Map dialog, as shown below.

   

   Note In many cases, it should be possible to create the required region of interest by simple thresholding. Refer to the topic Creating Threshold Segmentations for information about thistechnique.

3. Click OK.

   The watershed is evaluated with the labeled components in the multi-ROI as the seeds and the computed distance map as the landscape image.

   Wait for the expansion of the labeled objects to be computed and then overwritten into the initial multi-ROI.