Filters








301,424 Hits in 6.1 sec

Deformation Analysis for Shape Based Classification [chapter]

Polina Golland, W. Eric L. Grimson, Martha E. Shenton, Ron Kikinis
2001 Lecture Notes in Computer Science  
Given a classifier function in the feature space, we derive a deformation that corresponds to the differences between the two classes while ignoring shape variability within each class.  ...  The advantages of the presented algorithm include its generality (we derive it for a wide class of non-linear classifiers) as well as its flexibility in the choice of shape features used for classification  ...  a different region in the feature space and the corresponding deformation.  ... 
doi:10.1007/3-540-45729-1_54 fatcat:ax5cpz2eczhgze5pvmdrype6ce

Validation of continuously tagged MRI for the measurement of dynamic 3D skeletal muscle tissue deformation

Kevin M. Moerman, Andre M. J. Sprengers, Ciaran K. Simms, Rolf M. Lamerichs, Jaap Stoker, Aart J. Nederveen
2012 Medical Physics (Lancaster)  
In addition, the techniques were evaluated in-vivo for dynamic skeletal muscle tissue deformation measurement during indentation of the biceps region of the upper arm in a volunteer.  ...  Deformation is derived following tracking of tag surface triplet triangle intersections.  ...  The financial support agencies were not involved in designing and conducting this study, did not have access to the data, and were not involved in data analysis and/or preparation of this manuscript.  ... 
doi:10.1118/1.3685579 pmid:22482602 fatcat:3odtiybgnfevffkgi2ao4gv6ii

Construction of 'Support Vector' Machine Feature Spaces via Deformed Weyl-Heisenberg Algebra [article]

Shahram Dehdashti, Catarina Moreira, Abdul Karim Obeid, Peter Bruza
2020 arXiv   pre-print
The meta-kernel function applies associated revolution surfaces as feature spaces identified with non-linear coherent states.  ...  We show that deformed coherent states provide the theoretical foundation of a meta-kernel function, that is a kernel which in turn defines kernel functions.  ...  To the best of our knowledge, no such theory of meta-kernels presently exists. By means of a feature mapping, data is mapped into the feature space, represented by the deformed coherent space.  ... 
arXiv:2006.02904v1 fatcat:j5rq4xcfynhhxkkdcgoo4jlzou

MIFT: A Moment-Based Local Feature Extraction Algorithm

Hua-Zhen Zhang, Dong-Won Kim, Tae-Koo Kang, Myo-Taeg Lim
2019 Applied Sciences  
Although conventional scale invariant feature transform (SIFT)-based algorithms generally use difference of Gaussian (DoG) for feature extraction, they remain sensitive to more complicated deformations  ...  We propose a local feature descriptor based on moment.  ...  The SIFT-based descritpors are still sensitive to more complicated deformations because of the property of DoG used for the construction of scale-space.  ... 
doi:10.3390/app9071503 fatcat:yqr36yaqc5czhpold7qp7gnaja

SilSketch: Automated Sketch-Based Editing of Surface Meshes [article]

Johannes Zimmermann, Andrew Nealen, Marc Alexa
2007 Sketch-Based Interfaces and Modeling  
We introduce an over-sketching interface for feature-preserving surface mesh editing. The user sketches a stroke that is the suggested position of part of a silhouette of the displayed surface.  ...  silhouette part, selects a sub-region of the mesh to be modified, and feeds appropriately modified vertex positions together with the sub-mesh into a mesh deformation tool.  ...  The displacements for these vertices are derived from displacements in image-space.  ... 
doi:10.2312/sbm/sbm07/023-030 fatcat:qh625ccrjzggliwsrb4dziff5q

SilSketch

Johannes Zimmermann, Andrew Nealen, Marc Alexa
2007 Proceedings of the 4th Eurographics workshop on Sketch-based interfaces and modeling - SBIM '07  
We introduce an over-sketching interface for feature-preserving surface mesh editing. The user sketches a stroke that is the suggested position of part of a silhouette of the displayed surface.  ...  silhouette part, selects a sub-region of the mesh to be modified, and feeds appropriately modified vertex positions together with the sub-mesh into a mesh deformation tool.  ...  The displacements for these vertices are derived from displacements in image-space.  ... 
doi:10.1145/1384429.1384438 fatcat:zwt7py7ecjcgta53ocsr4kncna

Sketching contours

Johannes Zimmermann, Andrew Nealen, Marc Alexa
2008 Computers & graphics  
We introduce an over-sketching interface for feature-preserving surface mesh editing. The user sketches a stroke that is the suggested position of part of a silhouette of the displayed surface.  ...  The system then segments all image-space silhouettes of the projected surface, identifies among all silhouette segments the best matching part, derives vertices in the surface mesh corresponding to the  ...  The image-space projection of these vertices covers the detected part of the feature line. (4) New positions for the handle vertices are derived from the displacements in image-space between the projection  ... 
doi:10.1016/j.cag.2008.05.006 fatcat:v6gktpnddbbchegkzr267c54xa

Geometric Total Variation for Texture Deformation

Dmitriy Bespalov, Anders Dahl, Ali Shokoufandeh
2010 2010 20th International Conference on Pattern Recognition  
Accurate localization of features in the presence of unknown deformations is a crucial property for texture characterization.  ...  In this work we propose a novel variational method that we intend to use for estimating non-rigid texture deformation.  ...  ACKNOWLEDGMENTS This work is supported by Office of Naval Research grant ONR-N000140410363.  ... 
doi:10.1109/icpr.2010.1119 dblp:conf/icpr/BespalovDS10 fatcat:h26infglbjft5j2zom3dbvcrcq

Dimensional flow in the kappa-deformed spacetime

Anjana V., E. Harikumar
2015 Physical Review D  
These deformed diffusion equations are derived by applying Wick's rotation to the κ-deformed Schrödinger equations obtained from different choices of Klein-Gordon equations in the κ-deformed space-time  ...  We derive the modified diffusion equations defined on kappa-space-time and using these, investigate the change in the spectral dimension of kappa-space-time with the probe scale.  ...  But the higher derivative terms in the Laplacian (equivalently, Beltrami-Laplace operator) is a characteristic feature of κdeformed space-time.  ... 
doi:10.1103/physrevd.92.045014 fatcat:knnqizzl5ngbvl5rjowabjvkme

Diffusion Tensor Image Registration with Combined Tract and Tensor Features [chapter]

Qian Wang, Pew-Thian Yap, Guorong Wu, Dinggang Shen
2011 Lecture Notes in Computer Science  
We incorporate this attribute vector into a multi-scale registration framework where the moving image is warped to the space of the fixed image under the guidance of tract information at a more global  ...  To improve the accuracy of DT image registration, we design an attribute vector that encapsulates both tract and tensor information to serve as a voxel morphological signature for effective correspondence  ...  The registration of a fixed image and a moving image is cast as a problem of minimizing the overall distances, B , for tract derived features and T , for the tensor derived features, with a certain smooth  ... 
doi:10.1007/978-3-642-23629-7_25 fatcat:ts6o3hs3ojbl3dk2hzm6okwkye

Accelerated horizons and Planck-scale kinematics

Michele Arzano, Matteo Laudonio
2018 Physical Review D  
In the specific model of symmetry deformation considered it will turn out that a non-diverging density of modes close to the horizon can be achieved only by introducing a momentum space measure which violates  ...  We show that the non-trivial effects due to symmetry deformation manifest in a finite blueshift for field modes as measured by a Rindler observer approaching the horizon.  ...  This will prepare the ground for a derivation of the same concepts in the context of a quantum deformation of the same algebra.  ... 
doi:10.1103/physrevd.97.085004 fatcat:6ipr5dv5nzda5dggbmjjn7yesi

Image Morphing in Deep Feature Spaces: Theory and Applications

Alexander Effland, Erich Kobler, Thomas Pock, Marko Rajković, Martin Rumpf
2020 Journal of Mathematical Imaging and Vision  
The spatial discretization is based on a finite difference approximation in image space and a stable spline approximation in deformation space; the fully discrete model is optimized using the iPALM algorithm  ...  For this model, a variational time discretization of the Riemannian path energy is presented and the existence of discrete geodesic paths minimizing this energy is demonstrated.  ...  To view a copy of this licence, visit http://creativecomm ons.org/licenses/by/4.0/.  ... 
doi:10.1007/s10851-020-00974-5 pmid:33627956 pmcid:PMC7878289 fatcat:scswrgf3ibabdlaxlxfcdyxxwq

Structural studies of a new series of ester derivatives in cyclopropanol chemistry

L. Torre-Fernandez, S. Garcia-Granda, M.G. Suero
2008 Acta Crystallographica Section A Foundations of Crystallography  
ScRh3Bx exists in a wide range of boron concentration with the space group Pm-3m.  ...  A new two-component plastic flow model is proposed, which is appropriate for addressing the distinctive features of plastic flow localization in solids which cannot be explicitly interpreted in the framework  ...  ScRh3Bx exists in a wide range of boron concentration with the space group Pm-3m.  ... 
doi:10.1107/s0108767308085346 fatcat:flri3y7k75czvpcdrcr6qz26ci

Recognition of Protruding Objects in Highly Structured Surroundings by Structural Inference [chapter]

Vincent F. van Ravesteijn, Frans M. Vos, Lucas J. van Vliet
2009 Lecture Notes in Computer Science  
Recognition of objects in highly structured surroundings is a challenging task, because the appearance of target objects changes due to fluctuations in their surroundings.  ...  Due to the lack of knowledge about the target class, we also encounter a difficulty delimiting the non-target class.  ...  feature space.  ... 
doi:10.1007/978-3-642-02230-2_5 fatcat:aza6roagejepha3fwz65jfx4ai

KAZE Features [chapter]

Pablo Fernández Alcantarilla, Adrien Bartoli, Andrew J. Davison
2012 Lecture Notes in Computer Science  
In contrast, we detect and describe 2D features in a nonlinear scale space by means of nonlinear diffusion filtering.  ...  In this paper, we introduce KAZE features, a novel multiscale 2D feature detection and description algorithm in nonlinear scale spaces.  ...  Alcantarilla and Adrien Bartoli would like to acknowledge the support of ANR through project SYSEO. Andrew J. Davison was supported by ERC Starting Grant 210346.  ... 
doi:10.1007/978-3-642-33783-3_16 fatcat:bur7ygj47jfnppdgh7pr6eifs4
« Previous Showing results 1 — 15 out of 301,424 results