{{More citations needed|date=August 2019}}

'''GrowCut''' is an interactive segmentation algorithm. It uses Cellular Automaton as an image model. Automata evolution models segmentation process. Each cell of the automata has some label (in case of binary segmentation - 'object', 'background' and 'empty'). During automata evolution some cells capture their neighbours, replacing their labels.

In GrowCut, a user vaguely draws some strokes inside the object of interest with an object brush, and outside the object with a background brush. In simple cases, only a few strokes suffice for segmentation. <!-- Deleted image removed: thumb|GrowCut demo --> == References == * {{cite conference | author=V. Vezhnevets, V. Konouchine | title=Grow-Cut" - Interactive Multi-Label N-D Image Segmentation | book-title=Proc. Graphicon | year=2005 | pages=150&ndash;156 | url=http://www.graphicon.ru/oldgr/en/publications/text/gc2005vk.pdf }}

== External links == * http://www.growcut.com - a Photoshop plugin, which implements GrowCut algorithm

{{DEFAULTSORT:Growcut Algorithm}} Category:Image segmentation