12,710 Hits in 15.5 sec

Fast Object Segmentation by Growing Minimal Paths from a Single Point on 2D or 3D Images

Fethallah Benmansour, Laurent D. Cohen
2008 Journal of Mathematical Imaging and Vision  
Detection of a variety of objects on real images is demonstrated. Using a similar idea, we can extract networks of minimal paths from a 3D image called Geodesic Meshing.  ...  Linking pairs of neighboring keypoints with minimal paths allows us to extract a closed contour from a 2D image.  ...  Acknowledgement This work was partially supported by ANR grant SURF-NT05-2-45825.  ... 
doi:10.1007/s10851-008-0131-0 fatcat:v6dscwu47far3htfafvgbtz56y

A geodesic voting method for the segmentation of tubular tree and centerlines

Youssef Rouchdy, Laurent D. Cohen
2011 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro  
We show results of the segmentation with this approach on 2D angiogram images. This approach can be extended to 3D images in a straight forward manner.  ...  Many authors have used minimal cost paths, or similarly geodesics relative to a weight potential P, to find a vessel between two end points.  ...  Each end point allows to extract a branch of the tree as a minimal path from this point to the source point, the points located on the minimal path are very likely located on the vessel of interest.  ... 
doi:10.1109/isbi.2011.5872566 dblp:conf/isbi/RouchdyC11 fatcat:3kfly6mujbga7ajmux42cl4bdy

Finding a Closed Boundary by Growing Minimal Paths from a Single Point on 2D or 3D Images

Fethallah Benmansour, Stephane Bonneau, Laurent D. Cohen
2007 2007 IEEE 11th International Conference on Computer Vision  
Linking pairs of neighboring keypoints with minimal paths allows us to extract a closed contour from a 2D image. Detection of a variety of objects on real images is demonstrated.  ...  Using a similar same idea, we can extract networks of minimal paths from a 3D image called Geodesic Meshing.  ...  from a single point (or more if desired) initialized on the desired object boundary.  ... 
doi:10.1109/iccv.2007.4409156 dblp:conf/iccv/BenmansourBC07 fatcat:llanudz4lfgstbjgslxhsbpdlu

A review of 3D vessel lumen segmentation techniques: Models, features and extraction schemes

David Lesage, Elsa D. Angelini, Isabelle Bloch, Gareth Funka-Lea
2009 Medical Image Analysis  
In this paper, we review state-of-the-art literature on vascular segmentation, with a particular focus on 3D contrast-enhanced imaging modalities (MRA and CTA).  ...  Despite the tremendous amount of past and on-going dedicated research, vascular segmentation remains a challenging task.  ...  Region-growing approaches From seed points or regions located inside a vessel, regiongrowing approaches incrementally segment an object by recruiting neighboring voxels based on some inclusion criteria  ... 
doi:10.1016/ pmid:19818675 fatcat:rroixlliubb6nfmvlhahdqtniq

Automatic Fuzzy-based Hybrid Approach for Segmentation and Centerline Extraction of Main Coronary Arteries

Khadega Khaled, Mohamed A., Khaled Mostafa
2017 International Journal of Advanced Computer Science and Applications  
Finally, the centerlines of the segmented arteries are extracted based on the segmented 3D binary volume using a skeletonization based method.  ...  Then, the well-known Fuzzy c-mean algorithm is employed to detect the seed points for the region growing algorithm resulting in 3D binary volume.  ...  Beginning from this seed points, axial aortic cross-sections are subsequently segmented by a 2D region growing technique.  ... 
doi:10.14569/ijacsa.2017.080633 fatcat:wd4o4yoeu5dqlg2ouw7xmimq34

Interactive seismic interpretation with piecewise global energy minimization

Thomas Hollt, Johanna Beyer, Fritz Gschwantner, Philipp Muigg, Helmut Doleisch, Gabor Heinemann, Markus Hadwiger
2011 2011 IEEE Pacific Visualization Symposium  
We introduce a combination of 2D and 3D minimal cost path and minimal cost surface tracing for extracting horizons with very little user input.  ...  Instead of interpreting the volume slice-by-slice in 2D, we propose 3D seismic interpretation based on well positions.  ...  Most proposed methods were based on simple networks of 2D minimal cost paths. A set of minimal cost paths in a 3D image, yet does not necessarily define a minimum cost surface.  ... 
doi:10.1109/pacificvis.2011.5742373 dblp:conf/apvis/HolltBGMDHH11 fatcat:f4s5duj5lzdznfly2zusy32vce

Segmentation of 3D tubular objects with adaptive front propagation and minimal tree extraction for 3D medical imaging

Laurent D. Cohen, Thomas Deschamps
2007 Computer Methods in Biomechanics and Biomedical Engineering  
FM allows segmentation of tubular structures by inflating a "long balloon" from a user given single point.  ...  Received B; revised B; in final form B) Q2 We present a new fast approach for segmentation of thin branching structures, like vascular trees, based on Fast-Marching (FM) and Level Set (LS) methods.  ...  When computing the minimal energy from a starting point, the Trial points correspond to the boundary of the visited points (a contour in 2D or a surface in 3D).  ... 
doi:10.1080/10255840701328239 pmid:17671862 fatcat:g4pn5lvuj5bf5mahdexqz523cq

Virtual finger boosts three-dimensional imaging and microsurgery as well as terabyte volume image visualization and analysis

Hanchuan Peng, Jianyong Tang, Hang Xiao, Alessandro Bria, Jianlong Zhou, Victoria Butler, Zhi Zhou, Paloma T. Gonzalez-Bellido, Seung W. Oh, Jichao Chen, Ananya Mitra, Richard W. Tsien (+6 others)
2014 Nature Communications  
We develop virtual finger (VF) to generate 3D curves, points and regions-of-interest in the 3D space of a volumetric image with a single finger operation, such as a computer mouse stroke, or click or zoom  ...  Alternatively, using the Imaris (Bitplane) software, a user may produce a 3D curve by first defining a parameterized starting location followed by region growing or tube-fitting.  ...  This work was mainly supported by Howard Hughes Medical Institute. H.P. is currently supported by the Allen Institute for Brain Science. R.W.T. and A.M. were supported by a grant MH071739 (MERIT).  ... 
doi:10.1038/ncomms5342 pmid:25014658 pmcid:PMC4104457 fatcat:tyku5bghrvfy7jivzlpd2oelve

Semantic labeling of 3D point clouds with object affordance for robot manipulation

David Inkyu Kim, Gaurav S. Sukhatme
2014 2014 IEEE International Conference on Robotics and Automation (ICRA)  
We propose a technique to extract geometric features from point cloud segments and build a classifier to predict associated object affordances.  ...  In this paper, we address the problem of semantic labeling 3D point clouds by object affordance (e.g., 'pushable', 'liftable').  ...  ACKNOWLEDGMENT This work was supported in part by the US National Science Foundation Robust Intelligence Program (grant IIS-1017134), and by the Defense Advanced Projects Research Agency under the Autonomous  ... 
doi:10.1109/icra.2014.6907679 dblp:conf/icra/KimS14a fatcat:7pyjnwsgx5emtpugnu26jzjloa

An energy-based three-dimensional segmentation approach for the quantitative interpretation of electron tomograms

A. Bartesaghi, G. Sapiro, S. Subramaniam
2005 IEEE Transactions on Image Processing  
Individual features in the tomogram are segmented using a novel robust algorithm that finds their boundaries as global minimal surfaces in a metric space defined by image features.  ...  The optimization is carried out in a transformed spherical domain with center the an interior point of the particle of interest, providing a proper setting for the fast and accurate minimization of the  ...  Orenstein for providing sections from HIV-infected macrophages, and Jonathan Lefman and Stanton Lee for assistance with the tomography.  ... 
doi:10.1109/tip.2005.852467 pmid:16190467 pmcid:PMC1698959 fatcat:i6kyvatlivg43lmsrl2j67fx3y

Interactive skeletonization of intensity volumes

Sasakthi S. Abeysinghe, Tao Ju
2009 The Visual Computer  
Our contributions include formulating the task of drawing 3D centerlines given 2D user inputs as a constrained optimization problem, solving this problem on a discrete graph using a shortest-path algorithm  ...  While skeletons are very useful for a range of image analysis tasks, it is extremely difficult to obtain skeletons with correct connectivity and shape from noisy inputs using automatic skeletonization  ...  This work is supported in part by NSF grant IIS-0705538.  ... 
doi:10.1007/s00371-009-0325-5 fatcat:3xhxas4tc5g7lefm77ssvjhpfi

Geodesic voting for the automatic extraction of tree structures. Methods and applications

Youssef Rouchdy, Laurent D. Cohen
2013 Computer Vision and Image Understanding  
We utilize a set of such geodesic paths to find a tubular tree structure by seeking minimal interaction. We introduce a new idea that we call Geodesic Voting or Geodesic Density.  ...  Many authors have used minimal cost paths, or geodesics relative to a local weighting potential P, to find a vessel pathway between two end points.  ...  Geodesic Voting for segmentation of tree structures With the Fast Marching method we can extract the minimal path between two points by backtracking from the end point to the source point.  ... 
doi:10.1016/j.cviu.2013.06.001 fatcat:gddj7zub6rdx3nmbifgy662av4

Globally minimal surfaces by continuous maximal flows

B. Appleton, H. Talbot
2006 IEEE Transactions on Pattern Analysis and Machine Intelligence  
The new algorithm is applied to segmentation in 2D and 3D medical images and to 3D reconstruction from a stereo image pair.  ...  The results in 2D agree remarkably well with an existing planar minimal contour algorithm and the results in 3D segmentation and reconstruction demonstrate that the new algorithm is free from grid bias  ...  The new algorithm has been applied to segmentation in 2D and 3D medical images and to 3D reconstruction from a stereo image pair.  ... 
doi:10.1109/tpami.2006.12 pmid:16402623 fatcat:6ankpqdbarewnfrthmh6vx3osu

Segmentation and Reconstruction Techniques for Modeling of Blood Vessel

Vrushali Sudhir, Pranali C.
2017 International Journal of Computer Applications  
Several studies describe different numerical approaches to reconstruct a modeling of blood vessels closest to reality by using medical imaging.  ...  Vascular diseases are nowadays one of the serious issues which have a huge impact on someone's life.  ...  Segmentation of coronary artery along with the centerline extraction is done by using Hessian filtering and the minimal path method.  ... 
doi:10.5120/ijca2017913392 fatcat:6jyulin3sfadjgdjddm2xa23hi

Fast colon centreline calculation using optimised 3D topological thinning

Robert J.T. Sadleir, Paul F. Whelan
2005 Computerized Medical Imaging and Graphics  
Topological thinning can be used to accurately identify the central path through a computer model of the colon generated using computed tomography colonography.  ...  This is achieved by using lookup tables to reduce the computational burden associated with the thinning process. q  ...  Acknowledgements The authors would like to thank Dr Helen Fenlon and Dr John Bruzzi from the Department of Radiology at the Mater Misercordiae Hospital, Dublin, Ireland for supplying the CTC datasets used  ... 
doi:10.1016/j.compmedimag.2004.10.002 pmid:15890252 fatcat:fjk5drmqzreudbidcdqhgci4sq
« Previous Showing results 1 — 15 out of 12,710 results