Imperial College London

ProfessorMichaelBronstein

Faculty of EngineeringDepartment of Computing

Chair in Machine Learning and Pattern Recognition
 
 
 
//

Contact

 

m.bronstein Website

 
 
//

Location

 

569Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Publication Type
Year
to

192 results found

Rubinstein O, Honen Y, Bronstein AM, Bronstein MM, Kimmel Ret al., 2009, 3D-color video camera, Pages: 1505-1509

We introduce a design of a coded light-based 3D color video camera optimized for build up cost as well as accuracy in depth reconstruction and acquisition speed. The components of the system include a monochromatic camera and an off-the-shelf LED projector synchronized by a miniature circuit. The projected patterns are captured and processed at a rate of 200 fps and allow for real-time reconstruction of both depth and color at video rates. The reconstruction and display are performed at around 30 depth profiles and color texture per second using a graphics processing unit (GPU). ©2009 IEEE.

Conference paper

Ovsjanikov M, Bronstein AM, Bronstein MM, Guibas LJet al., 2009, Shape Google: A computer vision approach to isometry invariant shape retrieval, Pages: 320-327

Feature-based methods have recently gained popularity in computer vision and pattern recognition communities, in applications such as object recognition and image retrieval. In this paper, we explore analogous approaches in the 3D world applied to the problem of non-rigid shape search and retrieval in large databases. ©2009 IEEE.

Conference paper

Bronstein AM, Bronstein MM, Bruckstein AM, Kimmel Ret al., 2009, Partial Similarity of Objects, or How to Compare a Centaur to a Horse, INTERNATIONAL JOURNAL OF COMPUTER VISION, Vol: 84, Pages: 163-183, ISSN: 0920-5691

Journal article

Bronstein AM, Bronstein MM, Kimmel R, 2009, Topology-Invariant Similarity of Nonrigid Shapes, INTERNATIONAL JOURNAL OF COMPUTER VISION, Vol: 81, Pages: 281-301, ISSN: 0920-5691

Journal article

Weber O, Devir YS, Bronstein AM, Bronstein MM, Kimmel Ret al., 2008, Parallel Algorithms for Approximation of Distance Maps on Parametric Surfaces, ACM TRANSACTIONS ON GRAPHICS, Vol: 27, ISSN: 0730-0301

Journal article

Bronstein AM, Bronstein MM, Kimmel R, 2008, Numerical Geometry of Non-Rigid Shapes, Publisher: Springer Science & Business Media, ISBN: 9780387733012

A gallery of colored images enhances the text. This book will be of interest to graduate students, researchers and professionals in different fields of mathematics, computer science and engineering.

Book

Bronstein AM, Bronstein MM, Bruckstein AM, Kimmel Ret al., 2008, Analysis of two-dimensional non-rigid shapes, INTERNATIONAL JOURNAL OF COMPUTER VISION, Vol: 78, Pages: 67-88, ISSN: 0920-5691

Journal article

Bronstein AM, Bronstein MM, 2008, Regularized Partial Matching of Rigid Shapes, 10th European Conference on Computer Vision (ECCV 2008), Publisher: SPRINGER-VERLAG BERLIN, Pages: 143-154, ISSN: 0302-9743

Conference paper

Bronstein AM, Bronstein MM, 2008, Not only size matters: regularized partial matching of nonrigid shapes, IEEE Conference on Computer Vision and Pattern Recognition, Publisher: IEEE, Pages: 947-952, ISSN: 1063-6919

Conference paper

Bronstein AM, Bronstein MM, Kimmel R, 2007, Calculus of nonrigid surfaces for geometry and texture manipulation, IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, Vol: 13, Pages: 902-913, ISSN: 1077-2626

Journal article

Bronstein AM, Bronstein MM, Kimmel R, 2007, Weighted distance maps computation on parametric three-dimensional manifolds, JOURNAL OF COMPUTATIONAL PHYSICS, Vol: 225, Pages: 771-784, ISSN: 0021-9991

Journal article

Bronstein AM, Bronstein MM, Bruckstein AM, Kimmel Ret al., 2007, Paretian similarity for partial comparison of non-rigid objects, 1st International Conference on Scale Space and Variational Methods in Computer Vision, Publisher: SPRINGER-VERLAG BERLIN, Pages: 264-+, ISSN: 0302-9743

Conference paper

Bronstein AM, Bronstein MM, Kimmel R, 2007, Rock, paper, and scissors: extrinsic vs. intrinsic similarity of non-rigid shapes, 11th IEEE International Conference on Computer Vision, Publisher: IEEE, Pages: 1941-1946, ISSN: 1550-5499

Conference paper

Bronstein AM, Bronstein MM, Kimmel R, 2007, Expression-invariant representations of faces, IEEE TRANSACTIONS ON IMAGE PROCESSING, Vol: 16, Pages: 188-197, ISSN: 1057-7149

Journal article

Bronstein AM, Bronstein MM, Kimmel R, 2007, Story of Cinderella - Biometrics and isometry-invariant distances, Workshop on Advanced 3D Imaging for Safety and Security held in Conjunction with the International Conference on Computer Vision and Pattern Recognition, Publisher: SPRINGER, Pages: 119-+

Conference paper

Raviv D, Bronstein AM, Bronstein MM, Kimmel Ret al., 2007, Symmetries of non-rigid shapes, 11th IEEE International Conference on Computer Vision, Publisher: IEEE, Pages: 2746-2752, ISSN: 1550-5499

Conference paper

Bronstein MM, Bronstein AM, Kimmel R, Yavneh Iet al., 2006, Multigrid multidimensional scaling, 12th Copper Mountain Conference on Multigrid Methods, Publisher: JOHN WILEY & SONS LTD, Pages: 149-171, ISSN: 1070-5325

Conference paper

Bronstein AM, Bronstein MM, Kimmel R, 2006, Generalized multidimensional scaling: A framework for isometry-invariant partial surface matching, PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, Vol: 103, Pages: 1168-1172, ISSN: 0027-8424

Journal article

Bronstein AM, Bronstein MM, Kimmel R, 2006, Facetoface : An isometric model for facial animation, 4th International Conference on Articulated Motion and Deformable Objects, Publisher: SPRINGER-VERLAG BERLIN, Pages: 38-47, ISSN: 0302-9743

Conference paper

Bronstein AM, Bronstein MM, Bruckstein AM, Kimmel Ret al., 2006, Matching two-dimensional articulated shapes using generalized multidimensional scaling, 4th International Conference on Articulated Motion and Deformable Objects, Publisher: SPRINGER-VERLAG BERLIN, Pages: 48-57, ISSN: 0302-9743

Conference paper

Rosman G, Bronstein AM, Bronstein MM, Kimmel Ret al., 2006, Manifold Analysis by Topologically Constrained Isometric Embedding, Conference of the World-Academy-of-Science-Engineering-and-Technology, Publisher: WORLD ACAD SCI, ENG & TECH-WASET, Pages: 301-307, ISSN: 1307-6884

Conference paper

Bronstein AM, Bronstein MM, Zibulevsky M, 2006, On separation of semitransparent dynamic images from static background, 6th International Conference on Independent Component Analysis and Blind Signal Separation, Publisher: SPRINGER-VERLAG BERLIN, Pages: 934-940, ISSN: 0302-9743

Conference paper

Bronstein AM, Bronstein MM, Kimmel R, 2006, Efficient computation of isometry-invariant distances between surfaces, SIAM JOURNAL ON SCIENTIFIC COMPUTING, Vol: 28, Pages: 1812-1836, ISSN: 1064-8275

Journal article

Bronstein AM, Bronstein MM, Kimmel R, 2006, Robust expression-invariant face recognition from partially missing data, 9th European Conference on Computer Vision (ECCV 2006), Publisher: SPRINGER-VERLAG BERLIN, Pages: 396-408, ISSN: 0302-9743

Conference paper

Bronstein AM, Bronstein MM, Zibulevsky M, Zeevi YYet al., 2005, "Unmixing" tissues: Sparse component analysis in multi-contrast MRI, Pages: 1282-1285, ISSN: 1522-4880

We pose the problem of tissue classification in MRI as a Blind Source Separation (BSS) problem and solve it by means of Sparse Component Analysis (SCA). Assuming that most MR images can be sparsely represented, we consider their optimal sparse representation. Sparse components define a physically-meaningful feature space for classification. We demonstrate our approach on simulated and real multi-contrast MRI data. The proposed framework is general in that it is applicable to other modalities of medical imaging as well, whenever the linear mixing model is applicable. © 2005 IEEE.

Conference paper

Bronstein AM, Bronstein MM, Kimmel R, 2005, Expression-invariant face recognition via spherical embedding, Pages: 756-759, ISSN: 1522-4880

Recently, it was proven empirically that facial expressions can be modelled as isometries, that is, geodesic distances on the facial surface were shown to be significantly less sensitive to facial expressions compared to Euclidean ones. Based on this assumption, the 3DFACE face recognition system was built. The system efficiently computes expression invariant signatures based on isometry-invariant representation of the facial surface. One of the crucial steps in the recognition system was embedding of the face geometric structure into a Euclidean (flat) space. Here, we propose to replace the flat embedding by a spherical one to construct isometric invariant representations of the facial image. We refer to these new invariants as spherical canonical images. Compared to its Euclidean counterpart, spherical embedding leads to notably smaller metric distortion. We demonstrate experimentally that representations with lower embedding error lead to better recognition. In order to efficiently compute the invariants we introduce a dissimilarity measure between the spherical canonical images based on the spherical harmonic transform. © 2005 IEEE.

Conference paper

Bronstein AM, Bronstein MM, Zibulevsky M, Zeevi YYet al., 2005, Blind separation of tissues in multi-modal MRI using Sparse Component Analysis, Pages: 1822-1825

We pose the problem of tissue classification in MRI as a Blind Source Separation (BSS) problem and solve it by means of Sparse Component Analysis (SCA). Assuming that most MR images can be sparsely represented, we consider their optimal sparse representation. Sparse components define a physically-meaningful feature space for classification. We demonstrate our approach on simulated and real multi-contrast MRI data. The proposed framework is general in that it is applicable to other modalities of medical imaging as well, whenever the linear mixing model is applicable. © 2005 IEEE.

Conference paper

Bronstein AM, Bronstein MM, Kimmel R, 2005, Isometric embedding of facial surfaces into script S sign<sup>3</sup>, Pages: 622-631, ISSN: 0302-9743

The problem of isometry-invariant representation and comparison of surfaces is of cardinal importance in pattern recognition applications dealing with deformable objects. Particularly, in three-dimensional face recognition treating facial expressions as isometries of the facial surface allows to perform robust recognition insensitive to expressions. Isometry-invariant representation of surfaces can be constructed by isometrically embedding them into some convenient space, and carrying out the comparison in that space. Presented here is a discussion on isometric embedding into script S sign3, which appears to be superior over the previously used Euclidean space in sense of the representation accuracy. © Springer-Verlag Berlin Heidelberg 2005.

Conference paper

Bronstein AM, Bronstein MM, Kimmel R, 2005, Three-dimensional face recognition, INTERNATIONAL JOURNAL OF COMPUTER VISION, Vol: 64, Pages: 5-30, ISSN: 0920-5691

Journal article

Bronstein AM, Bronstein MM, Zibulevsky M, 2005, Quasi maximum likelihood MIMO blind deconvolution: Super- and sub-Gaussianity versus consistency, IEEE Transactions on Signal Processing, Vol: 53, Pages: 2576-2579, ISSN: 1053-587X

In this correspondence, we consider the problem of multi-input multi output (MIMO) quasi maximum likelihood (QML) blind deconvolution. We examine two classes of estimators, which are commonly believed to be suitable for super- and sub-Gaussian sources. We state the consistency conditions and demonstrate a source distribution, for which the studied estimators are unsuitable, in the sense that they are inconsistent. © 2005 IEEE.

Journal article

This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-html.jsp Request URI: /respub/WEB-INF/jsp/search-html.jsp Query String: limit=30&id=00961504&person=true&page=5&respub-action=search.html