Snakes: Active contour models

By M. Kass, Andrew P. Witkin, Demetri Terzopoulos. 2004

16,408 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Graphics and Computer-Aided Design, 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 Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Segment Anything (2023, background): “Segmentation is a broad ﬁeld: there’s interactive segmentation [57, 109], edge detection [3], super pixelization [85], object proposal generation [2], foreground segmentation [94], semantic segmentation [90], instance segmentation [66], panoptic segmentation [59], etc .”
Getting to 99% Accuracy in Interactive Segmentation (2020, methodology): “[6, 13, 14]) have superseded prior works [1–4].”
Deep Interactive Object Selection (2016, neutral): “There are many interactive segmentation approaches proposed over the past decades, such as contour-based methods [19, 10] and bounding box methods [21].”
Fast Edge Detection Using Structured Forests (2014, neutral): “F”
Human Pose Estimation with Iterative Error Feedback (2015, background): “Classic spatial alignment and warping computer vision models, such as snakes, [20] and Active Appearance Models (AAMs) [6] have similar goals as the proposed IEF, but are not learned end-to-end – or learned at all – employ linear shape models and hand designed features and require slower gradient co”
A comparative evaluation of interactive segmentation algorithms (2010, neutral): “Ac ce pte d m an us cri pt Table 1 Algorithmic approaches to interactive segmentation Method Example Algorithm Thresholding Simple gray-scale thresholding Region Growing Seeded Region Growing* [8] Classifiers Simple Interactive Object Extraction* [9] Graph and MRF Models Interactive Graph Cuts* [10]”
Image Segmentation Using Deep Learning: A Survey (2020, methodology): “Numerous image segmentation algorithms have been developed in the literature, from the earliest methods, such as thresholding [4], histogram-based bundling, regiongrowing [5], k-means clustering [6], watershed methods [7], to more advanced algorithms such as active contours [8], graph cuts [9], cond”
Fiji - an Open Source platform for biological image analysis (2012, methodology): “3i ) or automatically with Active Contours 38 and Level Sets 39 algorithms integrated into TrakEM2.”
Using Prior Shapes in Geometric Active Contours in a Variational Framework (2002, background): “The classical snake model proposed by Kass et al. (1988) is formulated by minimizing the energy function: The first term in Eq.”
Deep Snake for Real-Time Instance Segmentation (2020, methodology): “Inspired by previous methods [21, 25], deep snake takes an initial contour as input and deforms it by regressing vertex-wise offsets.”
Multi-View Stereo Reconstruction and Scene Flow Estimation with a Global Image-Based Matching Score (2007, methodology): “Deformable surfaces These methods inherit from the active contour method pioneered in [15].”
SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation (2017, methodology): “…methods such as thresholding [25], region growing [1], edge detec-a tion and grouping [3], Markov Random Fields (MRFs) [21], active contour models [14], Mumford-Shah functional based frame partition [23], level sets [20], graph cut [29], mean shift [6], and their extensions and integrations [10,…”
Biometric Recognition Using 3D Ear Shape (2007, methodology): “From 497 people that participated in two or more image acquisition sessions, there were 415 who had good-quality 2D and 3D ear images in two or more sessions.”
Quantitative analysis of cryo-EM density map segmentation by watershed and scale-space filtering, and fitting of structures by alignment to regions (2010, background): “, 2006), active contours (Kass et al., 1988), level sets (Malladi et al.”
Object Instance Annotation With Deep Extreme Level Set Evolution (2019, methodology): “Edge based methods [23, 15, 7, 24, 8] mostly employ edge features in the external energy and evolve an initial curve to fit object boundaries.”
Computer-aided detection/diagnosis of breast cancer in mammography and ultrasound: a review. (2013, methodology): “The active contour model is a framework known as snake [86] which is applied as an edge segmentation technique.”