Skip to main content

Watershed Segmentation

Description​

Watershed segmentation is a method of image segmentation based on the idea of a topographic map. The image is considered as a topographic surface, where the intensity of each pixel is its height. The algorithm starts by flooding the surface from the local minima (valleys) and then separating the catchment basins of the resulting watersheds by a ridge network. The ridge network is defined as the set of pixels where the gradient magnitude is locally maximal.

This method is commonly used in image processing, particularly in tasks such as object detection, image analysis, and medical imaging.

Settings​

Colour Thresholds​

Please see Colour Thresholds Setting.

Morphological Operation Settings​

Please see Morphological Operation Setting.

Watershed Segmentation Settings​

Normalise​

A normalised distance map is an image where each pixel represents the distance from that pixel to the nearest object or feature in the image.

Normalise Threshold​

Threshold to obtain the peaks after normalised.

Box Filter Dimensions​

Detected box width and height filter.

Display Results​

Overlay Results​

Whether to draw the results on top of the image frame.

Overlay Opacity​

The opacity of the drawn overlay.