Now showing items 104-123 of 210

    • Mass-Preserving Maps for Registration and Visual Tracking 

      Haker, Steven; Tannenbaum, Allen R. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2001-12)
      We consider a new method for an important aspect of the visual tracking problem. Tracking in the presence of a disturbance is a classical control issue, but because of the highly uncertain nature of the disturbance, this ...
    • Mathematical Methods in Medical Image Processing 

      Angenent, Sigurd; Pichon, Eric; Tannenbaum, Allen R. (Georgia Institute of TechnologyAmerican Mathematical Society, 2006-07)
      In this paper, we describe some central mathematical problems in medical imaging. The subject has been undergoing rapid changes driven by better hardware and software. Much of the software is based on novel methods utilizing ...
    • Minimizing Flows for the Monge–Kantorovich Problem 

      Angenent, Sigurd; Haker, Steven; Tannenbaum, Allen R. (Georgia Institute of TechnologySociety for Industrial and Applied Mathematics, 2003)
      In this work, we formulate a new minimizing flow for the optimal mass transport (Monge–Kantorovich) problem. We study certain properties of the flow, including weak solutions as well as short- and long-term existence. ...
    • Missile Tracking Using Knowledge-Based Adaptive Thresholding 

      Haker, Steven; Sapiro, Guillermo; Tannenbaum, Allen R.; Washburn, Donald (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2001-10)
      We apply a knowledge-based segmentation method developed for still and video images to the problem of tracking missiles and high speed projectiles. Since we are only interested in segmenting a portion of the missile (namely, ...
    • Multi-Object Tracking Through Clutter Using Graph Cuts 

      Malcolm, James G.; Rathi, Yogesh; Tannenbaum, Allen R. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2007-10)
      The standard graph cut technique is a robust method for globally optimal image segmentations. However, because of its global nature, it is prone to capture outlying areas similar to the object of interest. This paper ...
    • Multi-resolution 3D Nonrigid Registration via Optimal Mass Transport on the GPU 

      Rehman, Tauseef ur; Pryor, Gallagher D.; Melonakos, John; Tannenbaum, Allen R. (Georgia Institute of Technology, 2007)
      In this paper we present computationally efficient implementation of the minimizing flow approach for optimal mass transport (OMT) with applications to non-rigid 3D image registration. Our implementation solves the OMT ...
    • Multigrid optimal mass transport for image registration and morphing 

      Rehman, Tauseef ur; Tannenbaum, Allen R. (Georgia Institute of TechnologySociety of Photo-Optical Instrumentation Engineers, 2007-01-29)
      In this paper we present a computationally efficient Optimal Mass Transport algorithm. This method is based on the Monge-Kantorovich theory and is used for computing elastic registration and warping maps in image registration ...
    • Multimodal Registration of White Matter Brain Data via Optimal Mass Transport 

      Rehman, Tauseef ur; Haber, Eldad; Pohl, Kilian M.; Haker, Steven; Halle, Michael; Talos, Florin; Wald, Lawrence L.; Kikinis, Ron; Tannenbaum, Allen R. (Georgia Institute of TechnologyInsight Software Consortium, 2008-09)
      The elastic registration of medical scans from different acquisition sequences is becoming an important topic for many research labs that would like to continue the post-processing of medical scans acquired via the new ...
    • Multiscale 3D Shape Analysis using Spherical Wavelets 

      Nain, Delphine; Haker, Steven; Bobick, Aaron; Tannenbaum, Allen R. (Georgia Institute of TechnologySpringer Verlag, 2005-10)
      Shape priors attempt to represent biological variations within a population. When variations are global, Principal Component Analysis (PCA) can be used to learn major modes of variation, even from a limited training set. ...
    • Neural Tractography Using An Unscented Kalman Filter 

      Malcolm, James G.; Shenton, Martha E.; Rathi, Yogesh (Georgia Institute of Technology, 2009)
      We describe a technique to simultaneously estimate a local neural fiber model and trace out its path. Existing techniques estimate the local fiber orientation at each voxel independently so there is no running knowledge ...
    • A New Distribution Metric for Image Segmentation 

      Sandhu, Romeil; Georgiou, Tryphon T.; Tannenbaum, Allen R. (Georgia Institute of TechnologySociety of Photo-Optical Instrumentation Engineers, 2008-02)
      In this paper, we present a new distribution metric for image segmentation that arises as a result in prediction theory. Forming a natural geodesic, our metric quantifies “distance” for two density functionals as the ...
    • Non-Euclidian metrics and the robust stabilization of systems with parameter uncertainty 

      Khargonekar, Pramod P.; Tannenbaum, Allen R. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 1985-10)
      This paper considers, from a complex function theoretic point of view, certain kinds of robust synthesis problems. In particular, we use a certain kind of metric on the disk (the "hyperbolic" metric) which allows us to ...
    • Non-linear shape approximation via the entropy scale space 

      Kimia, Benjamin B.; Tannenbaum, Allen R.; Zucker, Steven W. (Georgia Institute of TechnologyInternational Society for Optical Engineering, 1993-07)
      There are two classical approaches to approximating the shape of objects. The first is based on diffusion and often leads to the (Gaussian) smoothing of contour information. The resulting scale-space may often be viewed ...
    • Non-Rigid 2D-3D Pose Estimation and 2D Image Segmentation 

      Sandhu, Romeil; Dambreville, Samuel; Yezzi, Anthony; Tannenbaum, Allen R. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2009-06)
      In this work, we present a non-rigid approach to jointly solve the tasks of 2D-3D pose estimation and 2D image segmentation. In general, most frameworks which couple both pose estimation and segmentation assume that one ...
    • Nondistorting Flattening Maps and the 3-D Visualization of Colon CT Images 

      Haker, Steven; Angenent, Sigurd; Tannenbaum, Allen R.; Kikinis, Ron (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2000-07)
      Considers a novel three-dimensional (3-D) visualization technique based on surface flattening for virtual colonoscopy. Such visualization methods could be important in virtual colonoscopy because they have the potential ...
    • Nonlinear H∞ Optimization: A Causal Power Series Approach 

      Foias, Ciprian; Gu, Caixing; Tannenbaum, Allen R. (Georgia Institute of TechnologySociety for Industrial and Applied Mathematics, 1995-01)
      In this paper, using a power series methodology a design procedure applicable to analytic nonlinear plants is described. The technique used is a generalization of the linear H∞ theory. In contrast to previous work on this ...
    • Nonlinear Shape Prior from Kernel Space for Geometric Active Contours 

      Dambreville, Samuel; Rathi, Yogesh; Tannenbaum, Allen R. (Georgia Institute of TechnologySociety of Photo-Optical Instrumentation Engineers, 2006-01)
      The Geometric Active Contour (GAC) framework, which utilizes image information, has proven to be quite valuable for performing segmentation. However, the use of image information alone often leads to poor segmentation ...
    • A note on linear systems on K-3 surfaces 

      Tannenbaum, Allen R. (Georgia Institute of TechnologyAmerican Mathematical Society, 1982-09)
      A simple necessary and sufficient condition is given for a general member of the complete linear system Y to be irreducible and nonsingular where Y is a reduced, connected curve on a K-3 surface.
    • A novel method for pulmonary emboli visualization from high-resolution CT images 

      Pichon, Eric; Novak, Carol L.; Kiraly, Atilla P.; Naidich, David P. (Georgia Institute of TechnologySociety of Photo-Optical Instrumentation Engineers, 2004-02-15)
      Pulmonary Embolism (PE) is one of the most common causes of unexpected death in the US. The recent introduction of 16-slice Computed Tomography (CT) machines allows the acquisition of very high-resolution datasets. This ...
    • On approximately optimal H∞ controllers for distributed systems 

      Özbay, Hitay; Tannenbaum, Allen R. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 1989-12)
      The structure of all approximately optimal H∞ controllers for stable distributed plants with rational weights is elucidated. The finite- and infinite-dimensional parts of these H ∞ controllers are identified. It is shown ...