“RegionCut” — Interactive multi-label segmentation utilizing cellular automaton

Abstract

This paper addresses the problem of interactive image segmentation. We propose an extension of the GrowCut framework which follows Cellular Automaton theory and is comparable to a label propagation algorithm. Therefore, user labels are propagated according to Cellular Automaton until convergency. A common problem of GrowCut is the time consuming user initialization which requires distributed seeds. Our main contribution focuses on determining such an initialization utilizing GMMs and spherical coordinates. Furthermore we propose a new weight function based on the mean image gradient. According to our evaluation, our extensions result in a simplified user interaction and in better results in terms of accuracy and running time. Our experiments show that our method can compete with state-of-the-art energy minimization frameworks.

Hybrid positron emission tomography segmentation of heterogeneous lung tumors using 3D Slicer: improved GrowCut algorithm with threshold initialization

“…However, the algorithm is dependent on the correctness of user-marked labels. 22,23 To address this limitation, we provide a threshold-based initial estimate of the tumor and a 3-D background shell as the initial seeds. This automation has helped to reduce the intraobserver variability caused by the choice of initial seeds provided by the user.…”

“…2.2, the GrowCut algorithm is dependent on the accuracy of user-marked input labels. 22,23 To overcome this limitation, the initialization has been automated in the IGC algorithm and the process is described in detail below. An initial estimate of the tumor is obtained by setting a threshold in the Segment Editor module of the 3D Slicer.…”

A New Framework for Interactive Images Segmentation

“…Fully autonomous segmentation schemes often fail due to the diverse background in images, it has inûuenced a number of researchers towards the wide investigation on semi-automatic (interactive)multi label image segmentation as shown in Fig. 1 There exist several automata-based segmentation approaches [3][4][5][6][7], but their results are highly dependent on label seed-marks. This is because they only use the local smoothness information in automata evolution rules.…”

“…According to [3], the competition rules are deûned in such away that an attacking pixel can occupy the target pixel only if the attack force of the attacker is greater than or equal to the strength of that pixel. Growcut has multiple beneûts over the graph based globally optimizing segmentation techniqueslike graphcut and grabcut, but it is highly sensitive to the location of user-deûned seed pixels [5].…”

Color Image Segmentation Based on Secondary Watershed and GrowCut Algorithm

“…GrowCut algorithm is an interactive image segmentation algorithm on the basis of cell automata which introduced by Vezhnevets in 2006 [5], the algorithm possesses good robustness, it can be applied to any dimensional images, and complete the difficult segmentation tasks. Due to its distinctive advantages, GrowCut algorithm has attracted many researchers' attention recently [6][7][8]. The traditional algorithm requires user to mark the target foreground and background, literature [9]and literature [10] put forward the GrowCut algorithm which marked foreground and background by user's dotted line and rectangular marquee respectively, the former label foreground by light-colored dotted lines while dark line marks the background; The latter uses the rectangular marquee tool to surround the target area as the background, then conduct the same way to mark out the foreground in the surround area; For the two marking methods above, the correctly classified of foreground and background area determine the marker of initial seed accurate or not, seeds more or less, or even marker inaccurately will affect the convergence speed and segmentation result.…”