A Review of Statistical Approaches to Level Set Segmentation: Integrating Color, Texture, Motion and Shape

By Daniel Cremers, Mikaël Rousson, Rachid Deriche. 2007

1,158 citations recorded by the source corpus.

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

Occupancy Networks: Learning 3D Reconstruction in Function Space (2018, background): “This idea is related to classical level set [10, 14, 50] approaches to multi-view 3D reconstruction [18,24,32,40,53,78].”
Deep Level Sets: Implicit Surface Representations for 3D Shape Inference (2019, background): “Formulations for incorporating such priors in to the level set framework has been the topic of considerable research efforts, for an excellent review see [4].”
Active contours driven by local Gaussian distribution fitting energy (2009, methodology): “Instead of utilizing image gradient, region-based models typically aim to identify each region of interest by using a certain region descriptor, such as intensity, color, texture or motion, to guide the motion of the contour [20].”
Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (2017, methodology): “affinity like fully connected CRF, boundary neural fields (BNF) [1] first predicts object boundaries with FCN feature maps and then encodes the boundary information in the pair-wise potential to enhance the semantic segmentation quality.”
A survey of graph theoretical approaches to image segmentation (2013, methodology): “for image thresholding methods [24], medical image segmentation [25-26], statistical level set segmentation [27], 3D image segmentation [28], edge detection techniques [29] and so on.”
Object Instance Annotation With Deep Extreme Level Set Evolution (2019, background): “Exploiting texture, color and shape information has also been extensively studied [18].”
Cell Population Tracking and Lineage Construction with Spatiotemporal Context (2007, methodology): “The region energy Eregion is based on the Bayesian region-competition framework (Zhu and Yuille, 1996; Cremers et al., 2007): Eregion =− ∑”
A review of segmentation methods in short axis cardiac MR images (2011, methodology): “Methods based on a statistical model mainly fall into three categories: shape prior segmentation (Cremers et al., 2007), active shape and appearance models (Heimann and Meinzer, 2009) and atlas-based segmentation techniques (Rohlfing et al.”
A review of algorithms for medical image segmentation and their applications to the female pelvic cavity (2010, methodology): “Wavelet transform (Chui 1993) and common edge detection algorithms such as Canny edge detection (Canny 1986), Sobel edge detection and Laplacian edge detection (Davis 1975) belong to this type.”
Statistical shape models for 3D medical image segmentation: A review (2009, methodology): “As in the 2D case, this version is both faster and delivers better results than the Nelder–Mead optimization from Davies et al. (2002). An open source version of the algorithm was later presented in (Heimann et al., 2006). Whereas re-parameterization on the sphere currently is the most popular metho”
Instance segmentation of fallen trees in aerial color infrared imagery using active multi-contour evolution with fully convolutional network-based intensity priors (2021, methodology): “Instead of attempting to detect objects in axis-aligned bounding boxes, we maintain shape parametrizations and associated rigid transform parameters separately per instance, effectively evolving multiple active contours (Cremers et al., 2007) simultaneously.”
Deep learning tools for the measurement of animal behavior in neuroscience (2019, methodology): “Other computer vision techniques, such as using texture or color to segment the person from the background to create silhouettes (14, 15), or using so-called hand-crafted features with decoders (11, 12, 16) were also popular before deep learning ﬂourished.”
Machine Learning and Radiology (2012, background): “Level set-based segmentation methods provide a natural and flexible way to handle those complicated objects (Cremers et al., 2007; Malladi et al., 1995).”
Implicit Surface Representations As Layers in Neural Networks (2019, background): “Formulations for incorporating such priors in to the level set framework has been the topic of considerable research efforts, for an excellent review see [4].”
Histology image analysis for carcinoma detection and grading (2012, background): “A review of recent active contours can be seen in [35,64,102].”
TouchCut: Fast image and video segmentation using single-touch interaction (2014, methodology): “We extend our system on still images to video sequences in Sec.”