“GrowCut” - Interactive Multi-Label N-D Image Segmentation By Cellular Automata

By Vladimir Vezhnevets. 2005

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Interactive Object Selection (2016, methodology): “Strokebased methods are popular, and use a number of underlying algorithms, including normalized cuts [22], graph cut [2, 11, 26], geodesics [1, 4], the combination of graph cut and geodesics [20, 9] and random walks [8].”
Interactive Full Image Segmentation by Considering All Regions Jointly (2018, background): “Several older works on interactive segmentation handle multiple labels in a single image [39, 40, 50, 53].”
Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review (2017, methodology): “[119] utilised an algorithm called Grow cut [148].”
Interactive Image Segmentation via Backpropagating Refinement Scheme (2019, methodology): “Experiments demonstrated that the proposed algorithm outperforms the conventional algorithms [11, 10, 3, 52, 50, 2, 27, 26] on the GrabCut [42], Berkeley [34], DAVIS [37], and SBD [12] datasets.”
A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation (2018, background): “In other representative research, Vezhnevets and Konouchine [6] propose GrowCut which iteratively updates labels of pixels based on cellular automaton [24].”
Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans (2016, methodology): “All the MORPH features are derived from manual outlines from experienced medical doctors and image segmentation results from the DRLSE level set 43 and grow-cut 44 methods.”
Regional Interactive Image Segmentation Networks (2017, unknown): “(e) MS COCO unseen categories RIS-Net (ours) iFCN [29] Random walker [11] Euclidean star convexity [12] Geodesic star convexity [12] Geodesic matting [1] Growcut [26] Graph cut [4]”
Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks (2017, methodology): “Therefore, we produce the final segmentation map by leveraging a parallel integration approach based on cellular automata (CA) [42]–[44].”
UI-Net: Interactive Artificial Neural Networks for Iterative Image Segmentation Based on a User Model (2017, unknown): “The interactive learning-based system is evaluated w.r.t. the well-known U-net [RFB15] without a user model and GrowCut [VK05, AGSM16] segmentation methods via the Sørensen-Dice coefﬁcient (Dice) [Dic45].”
Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning (2017, methodology): “BIFSeg was also compared with other interactive segmentation methods: GrabCut [20], SlicSeg [21] and Random Walks [3] for 2D segmentation, and GeoS [4], GrowCut [28] and 3D GrabCut [29] for 3D segmentation.”
PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click (2020, background): “Many interactive segmentation methods have been proposed in the past decades using many different interaction types such as bounding boxes [16, 29, 49, 57], contours [1,6, 26,45], strokes [5,31,51,53] and clicks [25,28,34,40,41,58].”