GeoS: Geodesic Image Segmentation

By Antonio Criminisi, Toby Sharp, Andrew Blake. 2008

311 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Iterative Interaction Training for Segmentation Editing Networks (2018, neutral): “To address the need for editing, interactive segmentation algorithms have been proposed such as GrabCut, GeoS or Random Walker [14,3,5] that allow operators to modify segmentations.”
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].”
Decision Forests for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning (2011, background): “Very efficient geodesic distance transform algorithms exist [22].”
A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis (2019, methodology): “They combine user interactions with CNNs through geodesic distance transforms Criminisi et al. (2008), and these user interactions are integrated as hard constraints into a Conditional Random Field, inspired by Zheng et al. (2015).”
Saliency-Aware Video Object Segmentation (2018, background): “It has been shown to be effective for supervised segmentation where user provides seeds [16], [17], [18], [19].”
Saliency-aware geodesic video object segmentation (2015, methodology): “In this paper, we try to introduce geodesic distance into our totally automatic segmentation framework, which is different with previous approaches [3, 25, 2, 10] that require careful user assistance.”
Geodesic Saliency Using Background Priors (2012, background): “Because of its linear complexity in the number of graph nodes and sequential memory access (therefore cache friendly), it is extremely fast and also used in interactive image segmentation [31, 32].”
Content-Aware Multi-Level Guidance for Interactive Instance Segmentation (2019, methodology): “Other methods include Graph Cuts [7], Random Walk [18] and GeoS [13] though more recent methods [32, 35, 36, 52, 53] approach the problem with deep learning architectures such as convolutional neural networks (CNNs).”
Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation (2015, methodology): “Recently, Crimisi et al. [84] proposed to use geodesic distance transform to ﬁlter the cost volume, which can produce results comparable to the global optimization methods and can better capture the edges at the weak boundaries.”
Nonparametric higher-order learning for interactive segmentation (2010, background): “During the last decade, the main research directions on interactive segmentation algorithms are focused on Graph Cuts [4][16] to find the minimum cut between the foreground and background seeds via a maximum flow computation, Random Walker [9][12] to determine the labels via the seed propagation on ”
Multi-Atlas Segmentation of Biomedical Images: A Survey (2014, background): “…are typically obtained by the meticulous and costly eﬀort of a domain-speciﬁc expert who relies on an interactive visualization software, such as (Criminisi et al., 2008; Heiberg et al., 2010; Pieper et al., 2004; Yushkevich et al., 2006), and might exploit multiple imaging modalities, while…”
Power Watershed: A Unifying Graph-Based Optimization Framework (2011, background): “We prove several theoretical properties of this new class of watershed and then give an algorithm for minimizing the energy associated with this generalized watershed model.”
Decision Forests: A Unified Framework for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning (2012, background): “Very efficient geodesic distance transform algorithms exist [23].”
Geodesic star convexity for interactive image segmentation (2010, background): “Using the above definition, one can define the geodesic distance as in [4]: d g (a, b) = min Γ∈P a,b L(Γ) , Γ a,b = arg min Γ∈P a,b L(Γ) (6) where P a,b denotes the set of all discrete paths between two grid points a and b. Note that unlike [2], we are interested in the geodesic path Γ a,b rather…”
MultiSeg: Semantically Meaningful, Scale-Diverse Segmentations From Minimal User Input (2019, methodology): “Interactive Image Segmentation: Early interactive image segmentation methods mainly exploit boundary properties for segmentation [17, 29] while more recent approaches are based on graphical models, such as graph cut [4, 21, 33], random walker [11] and geodesic approaches [2, 7, 31].”
iCoseg: Interactive co-segmentation with intelligent scribble guidance (2010, methodology): “The most commonly used smoothness term in energy minimization based segmentation methods [11, 12, 22] is the contrast sensitive Potts model:”
PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click (2020, methodology): “For example, [5,31,49] adopt graphical models, [18] employs random walker and [3, 11, 47] are based on geodesic approaches.”