The Watershed Image Labeling creates a *.g32 index image from the gray value image. Thus, the result could be used, e.g., in GrainFind to reconnect over-segmented objects and obtain grain statistics.

The name for the file and folder containing the results can be entered in the Result File Name (*.gdr) box. The default name can be kept, or a new name can be chosen, fitting the current project.

The parameters and the results are the same as for the Watershed (Supervoxel) image filter.

Additionally, it can be selected to label components as background. The background components are labeled with index 0.

If Filter Background Components by Threshold is selected, the watershed components with a mean gray value lower than the threshold given for Background Threshold are considered as background.

If Filter Background Components by Size is selected, the watershed components that consist of less voxels than the given Number of Voxels are considered as background.

Check both background component filters to label the components as background, that have a mean gray value lower than the given threshold, as well as consisting of less voxels than the given number of voxels.

Click Apply to run the Watershed Image Labeling process.

While the Watershed (Supervoxel) changes the image in the 2D Slice Visualization section, the Watershed Image Labeling does not. Load the results from the Result Viewer as explained here.

In the following example, the same image as for the Watershed (Supervoxel) filter is considered. For the Watershed Image Labeling the same parameters are used. Additionally, Filter Background Components by Threshold was checked and a Background Threshold of 120.5 was entered. Thus, all components with a gray-value lower than 120.5 were assigned to index 0, which is colored in white.