- scipy.ndimage.watershed_ift(input, markers, structure=None, output=None)[source]#
Apply watershed from markers using image foresting transform algorithm.
Markers are points within each watershed that form the beginning of the process. Negative markers are considered background markers which are processed after the other markers.
- structurestructure element, optional
A structuring element defining the connectivity of the object can be provided. If None, an element is generated with a squared connectivity equal to one.
- outputndarray, optional
An output array can optionally be provided. The same shape as input.
Output. Same shape as input.
A.X. Falcao, J. Stolfi and R. de Alencar Lotufo, “The image foresting transform: theory, algorithms, and applications”, Pattern Analysis and Machine Intelligence, vol. 26, pp. 19-29, 2004.