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

Ovsjanikov M, Corman E, Bronstein M, Rodolà E, Ben-Chen M, Guibas L, Chazal F, Bronstein Aet al., 2017, Computing and processing correspondences with functional maps

Notions of similarity and correspondence between geometric shapes and images are central to many tasks in geometry processing, computer vision, and computer graphics. The goal of this course is to familiarize the audience with a set of recent techniques that greatly facilitate the computation of mappings or correspondences between geometric datasets, such as 3D shapes or 2D images by formulating them as mappings between functions rather than points or triangles. Methods based on the functional map framework have recently led to state-of-the-art results in problems as diverse as non-rigid shape matching, image co-segmentation and even some aspects of tangent vector field design. One challenge in adopting these methods in practice, however, is that their exposition often assumes a significant amount of background in geometry processing, spectral methods and functional analysis, which can make it difficult to gain an intuition about their performance or about their applicability to real-life problems. In this course, we try to provide all the tools necessary to appreciate and use these techniques, while assuming very little background knowledge. We also give a unifying treatment of these techniques, which may be difficult to extract from the individual publications and, at the same time, hint at the generality of this point of view, which can help tackle many problems in the analysis and creation of visual content. This course is structured as a half day course. We will assume that the participants have knowledge of basic linear algebra and some knowledge of differential geometry, to the extent of being familiar with the concepts of a manifold and a tangent vector space. We will discuss in detail the functional approach to finding correspondences between non-rigid shapes, the design and analysis of tangent vector fields on surfaces, consistent map estimation in networks of shapes and applications to shape and image segmentation, shape variability analysis, and other ar

Conference paper

Bronstein MM, Bruna J, LeCun Y, Szlam A, Vandergheynst Pet al., 2017, Geometric Deep Learning Going beyond Euclidean data, IEEE SIGNAL PROCESSING MAGAZINE, Vol: 34, Pages: 18-42, ISSN: 1053-5888

Journal article

Litany O, Rodolà E, Bronstein AM, Bronstein MMet al., 2017, Fully Spectral Partial Shape Matching, Computer Graphics Forum, Vol: 36, Pages: 247-258, ISSN: 0167-7055

© 2017 The Author(s) Computer Graphics Forum © 2017 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd. We propose an efficient procedure for calculating partial dense intrinsic correspondence between deformable shapes performed entirely in the spectral domain. Our technique relies on the recently introduced partial functional maps formalism and on the joint approximate diagonalization (JAD) of the Laplace-Beltrami operators previously introduced for matching non-isometric shapes. We show that a variant of the JAD problem with an appropriately modified coupling term (surprisingly) allows to construct quasi-harmonic bases localized on the latent corresponding parts. This circumvents the need to explicitly compute the unknown parts by means of the cumbersome alternating minimization used in the previous approaches, and allows performing all the calculations in the spectral domain with constant complexity independent of the number of shape vertices. We provide an extensive evaluation of the proposed technique on standard non-rigid correspondence benchmarks and show state-of-the-art performance in various settings, including partiality and the presence of topological noise.

Journal article

Rodolà E, Cosmo L, Bronstein MM, Torsello A, Cremers Det al., 2017, Partial functional correspondence, Computer Graphics Forum, Vol: 36, Pages: 222-236

Journal article

Boyarski A, Bronstein AM, Bronstein MM, 2017, Subspace least squares multidimensional scaling, Pages: 681-693, ISSN: 0302-9743

© Springer International Publishing AG 2017. Multidimensional Scaling (MDS) is one of the most popular methods for dimensionality reduction and visualization of high dimensional data. Apart from these tasks, it also found applications in the field of geometry processing for the analysis and reconstruction of nonrigid shapes. In this regard, MDS can be thought of as a shape from metric algorithm, consisting of finding a configuration of points in the Euclidean space that realize, as isometrically as possible, some given distance structure. In the present work we cast the least squares variant of MDS (LS-MDS) in the spectral domain. This uncovers a multiresolution property of distance scaling which speeds up the optimization by a significant amount, while producing comparable, and sometimes even better, embeddings.

Conference paper

Rodolà E, Cosmo L, Litany O, Bronstein MM, Bronstein AM, Audebert N, Ben Hamza A, Boulch A, Castellani U, Do MN, Duong AD, Furuya T, Gasparetto A, Hong Y, Kim J, Le Saux B, Litman R, Masoumi M, Minello G, Nguyen HD, Nguyen VT, Ohbuchi R, Pham VK, Phan TV, Rezaei M, Torsello A, Tran MT, Tran QT, Truong B, Wan L, Zou Cet al., 2017, SHREC'17: Deformable shape retrieval with missing parts, Pages: 85-94, ISSN: 1997-0463

© 2017 The Eurographics Association. Partial similarity problems arise in numerous applications that involve real data acquisition by 3D sensors, inevitably leading to missing parts due to occlusions and partial views. In this setting, the shapes to be retrieved may undergo a variety of transformations simultaneously, such as non-rigid deformations (changes in pose), topological noise, and missing parts - a combination of nuisance factors that renders the retrieval process extremely challenging. With this benchmark, we aim to evaluate the state of the art in deformable shape retrieval under such kind of transformations. The benchmark is organized in two sub-challenges exemplifying different data modalities (3D vs. 2.5D). A total of 15 retrieval algorithms were evaluated in the contest; this paper presents the details of the dataset, and shows thorough comparisons among all competing methods.

Conference paper

Cosmo L, Rodola E, Masci J, Torsello A, Bronstein MMet al., 2016, Matching deformable objects in clutter, Pages: 1-10

© 2016 IEEE. We consider the problem of deformable object detection and dense correspondence in cluttered 3D scenes. Key ingredient to our method is the choice of representation: we formulate the problem in the spectral domain using the functional maps framework, where we seek for the most regular nearly-isometric parts in the model and the scene that minimize correspondence error. The problem is initialized by solving a sparse relaxation of a quadratic assignment problem on features obtained via data-driven metric learning. The resulting matching pipeline is solved efficiently, and yields accurate results in challenging settings that were previously left unexplored in the literature.

Conference paper

Eynard D, Rodola E, Glashoff K, Bronstein MMet al., 2016, Coupled functional maps, Pages: 399-407

© 2016 IEEE. Classical formulations of the shape matching problem involve the definition of a matching cost that directly depends on the action of the desired map when applied to some input data. Such formulations are typically one-sided - they seek for a mapping from one shape to the other, but not vice versa. In this paper we consider an unbiased formulation of this problem, in which we solve simultaneously for a low-distortion map relating the two given shapes and its inverse. We phrase the problem in the spectral domain using the language of functional maps, resulting in an especially compact and efficient optimization problem. The benefits of our proposed regularization are especially evident in the scarce data setting, where we demonstrate highly competitive results with respect to the state of the art.

Conference paper

Melzi S, Rodola E, Castellani U, Bronstein MMet al., 2016, Shape analysis with anisotropic windowed Fourier transform, Pages: 470-478

© 2016 IEEE. We propose Anisotropic Windowed Fourier Transform (AWFT), a framework for localized space-frequency analysis of deformable 3D shapes. With AWFT, we are able to extract meaningful intrinsic localized orientation-sensitive structures on surfaces, and use them in applications such as shape segmentation, salient point detection, feature point description, and matching. Our method outperforms previous approaches in the considered applications.

Conference paper

Lahner Z, Rodola E, Schmidt FR, Bronstein MM, Cremers Det al., 2016, Efficient Globally Optimal 2D-to-3D Deformable Shape Matching, Pages: 2185-2193, ISSN: 1063-6919

© 2016 IEEE. We propose the first algorithm for non-rigid 2D-to-3D shape matching, where the input is a 2D query shape as well as a 3D target shape and the output is a continuous matching curve represented as a closed contour on the 3D shape. We cast the problem as finding the shortest circular path on the product 3-manifold of the two shapes. We prove that the optimal matching can be computed in polynomial time with a (worst-case) complexity of O(mn2 log(n)), wherem and n denote the number of vertices on the 2D and the 3D shape respectively. Quantitative evaluation confirms that the method provides excellent results for sketch-based deformable 3D shape retrieval.

Conference paper

Ovsjanikov M, Corman E, Bronstein M, Rodolà E, Ben-Chen M, Guibas L, Chazal F, Bronstein Aet al., 2016, Computing and processing correspondences with functional maps

Notions of similarity and correspondence between geometric shapes and images are central to many tasks in geometry processing, computer vision, and computer graphics. The goal of this course is to familiarize the audience with a set of recent techniques that greatly facilitate the computation of mappings or correspondences between geometric datasets, such as 3D shapes or 2D images by formulating them as mappings between functions rather than points or triangles. Methods based on the functional map framework have recently led to state-of-the-art results in problems as diverse as non-rigid shape matching, image co-segmentation and even some aspects of tangent vector field design. One challenge in adopting these methods in practice, however, is that their exposition often assumes a significant amount of background in geometry processing, spectral methods and functional analysis, which can make it difficult to gain an intuition about their performance or about their applicability to real-life problems. In this course, we try to provide all the tools necessary to appreciate and use these techniques, while assuming very little background knowledge. We also give a unifying treatment of these techniques, which may be difficult to extract from the individual publications and, at the same time, hint at the generality of this point of view, which can help tackle many problems in the analysis and creation of visual content. This course is structured as a half day course. We will assume that the participants have knowledge of basic linear algebra and some knowledge of differential geometry, to the extent of being familiar with the concepts of a manifold and a tangent vector space. We will discuss in detail the functional approach to finding correspondences between non-rigid shapes, the design and analysis of tangent vector fields on surfaces, consistent map estimation in networks of shapes and applications to shape and image segmentation, shape variability analysis, and other ar

Conference paper

Masci J, Rodolà E, Boscaini D, Bronstein MM, Li Het al., 2016, Geometric deep learning

Conference paper

Pickup D, Sun X, Rosin PL, Martin RR, Cheng Z, Lian Z, Aono M, Hamza AB, Bronstein A, Bronstein M, Bu S, Castellani U, Cheng S, Garro V, Giachetti A, Godil A, Isaia L, Han J, Johan H, Lai L, Li B, Li C, Li H, Litman R, Liu X, Liu Z, Lu Y, Sun L, Tam G, Tatsuma A, Ye Jet al., 2016, Shape Retrieval of Non-rigid 3D Human Models, International Journal of Computer Vision, Vol: 120, Pages: 169-193, ISSN: 0920-5691

© 2016, The Author(s). 3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. We extend our recent paper which provided a benchmark for testing non-rigid 3D shape retrieval algorithms on 3D human models. This benchmark provided a far stricter challenge than previous shape benchmarks. We have added 145 new models for use as a separate training set, in order to standardise the training data used and provide a fairer comparison. We have also included experiments with the FAUST dataset of human scans. All participants of the previous benchmark study have taken part in the new tests reported here, many providing updated results using the new data. In addition, further participants have also taken part, and we provide extra analysis of the retrieval results. A total of 25 different shape retrieval methods are compared.

Journal article

Biasotti S, Cerri A, Bronstein A, Bronstein Met al., 2016, Recent Trends, Applications, and Perspectives in 3D Shape Similarity Assessment, Computer Graphics Forum, Vol: 35, Pages: 87-119, ISSN: 0167-7055

© 2015 The Authors Computer Graphics Forum © 2015 The Eurographics Association and John Wiley & Sons Ltd. The recent introduction of 3D shape analysis frameworks able to quantify the deformation of a shape into another in terms of the variation of real functions yields a new interpretation of the 3D shape similarity assessment and opens new perspectives. Indeed, while the classical approaches to similarity mainly quantify it as a numerical score, map-based methods also define (dense) shape correspondences. After presenting in detail the theoretical foundations underlying these approaches, we classify them by looking at their most salient features, including the kind of structure and invariance properties they capture, as well as the distances and the output modalities according to which the similarity between shapes is assessed and returned. We also review the usage of these methods in a number of 3D shape application domains, ranging from matching and retrieval to annotation and segmentation. Finally, the most promising directions for future research developments are discussed.

Journal article

Litany O, Rodolà E, Bronstein AM, Bronstein MM, Cremers Det al., 2016, Non-rigid puzzles, Computer Graphics Forum, Vol: 35, Pages: 135-143

Journal article

Boscaini D, Masci J, Rodolà E, Bronstein MM, Cremers Det al., 2016, Anisotropic diffusion descriptors, 37th Annual Conference of the European Association for Computer Graphics, Pages: 431-441

Conference paper

Pokrass J, Bronstein AM, Bronstein MM, Sprechmann P, Sapiro Get al., 2016, Sparse models for intrinsic shape correspondence, Mathematics and Visualization, Pages: 211-230

© 2016, Springer International Publishing Switzerland. We present a novel sparse modeling approach to non-rigid shape matching using only the ability to detect repeatable regions. As the input to our algorithm, we are given only two sets of regions in two shapes; no descriptors are provided so the correspondence between the regions is not know, nor do we know how many regions correspond in the two shapes. We show that even with such scarce information, it is possible to establish very accurate correspondence between the shapes by using methods from the field of sparse modeling, being this, the first non-trivial use of sparse models in shape correspondence. We formulate the problem of permuted sparse coding, in which we solve simultaneously for an unknown permutation ordering the regions on two shapes and for an unknown correspondence in functional representation. We also propose a robust variant capable of handling incomplete matches. Numerically, the problem is solved efficiently by alternating the solution of a linear assignment and a sparse coding problem. The proposed methods are evaluated qualitatively and quantitatively on standard benchmarks containing both synthetic and scanned objects.

Book chapter

Svoboda J, Masci J, Bronstein MM, 2016, Palmprint recognition via discriminative index learning, Pages: 4232-4237, ISSN: 1051-4651

© 2016 IEEE. In the past years, deep convolutional neural networks (CNNs) have become extremely popular in the computer vision and pattern recognition community. The computational power of modern processors, efficient stochastic optimization algorithms, and large amounts of training data allowed training complex tasks-specific features directly from the data in an end-to-end fashion, as opposed to the traditional way of using hand-crafted feature descriptors. CNNs are currently state-of-the-art methods in many computer vision problems, and have been successfully used in biometric applications such as face, fingerpring, and voice recognition. In palmprint recognition applications, CNNs have not yet been explored, and the majority of methods still rely on hand-crafted representations which do not scale well to large datasets and that usually require a complex manual parameter tuning. In this work, we show that CNNs can be successfully used for palmprint recognition. The training of our network uses a novel loss function related to the d-prime index, which allows to achieve a better genuine/impostor score distribution separation than previous approaches with only little training data required. Our approach does not require cumbersome parameter tuning and achieves state-of-the-art results on the standard IIT Delhi and CASIA palmprint datasets.

Conference paper

Cosmo L, Rodolà E, Bronstein MM, Torsello A, Cremers D, Sahillioǧlu Yet al., 2016, SHREC'16: Partial matching of deformable shapes, Pages: 61-67, ISSN: 1997-0463

© 2016 The Eurographics Association. Matching deformable 3D shapes under partiality transformations is a challenging problem that has received limited focus in the computer vision and graphics communities. With this benchmark, we explore and thoroughly investigate the robustness of existing matching methods in this challenging task. Participants are asked to provide a point-to-point correspondence (either sparse or dense) between deformable shapes undergoing different kinds of partiality transformations, resulting in a total of 400 matching problems to be solved for each method - making this benchmark the biggest and most challenging of its kind. Five matching algorithms were evaluated in the contest; this paper presents the details of the dataset, the adopted evaluation measures, and shows thorough comparisons among all competing methods.

Conference paper

Lähner Z, Rodolà E, Bronstein MM, Cremers D, Burghard O, Cosmo L, Dieckmann A, Klein R, Sahillioǧlu Yet al., 2016, SHREC'16: Matching of deformable shapes with topological noise, Pages: 55-60, ISSN: 1997-0463

© 2016 The Eurographics Association. A particularly challenging setting of the shape matching problem arises when the shapes being matched have topological artifacts due to the coalescence of spatially close surface regions - a scenario that frequently occurs when dealing with real data under suboptimal acquisition conditions. This track of the SHREC'16 contest evaluates shape matching algorithms that operate on 3D shapes under synthetically produced topological changes. The task is to produce a pointwise matching (either sparse or dense) between 90 pairs of shapes, representing the same individual in different poses but with different topology. A separate set of 15 shapes with ground-truth correspondence was provided as training data for learning-based techniques and for parameter tuning. Three research groups participated in the contest; this paper presents the track dataset, and describes the different methods and the contest results.

Conference paper

Boscaini D, Masci J, Rodolà E, Bronstein Met al., 2016, Learning shape correspondence with anisotropic convolutional neural networks, Pages: 3197-3205, ISSN: 1049-5258

© 2016 NIPS Foundation - All Rights Reserved. Convolutional neural networks have achieved extraordinary results in many computer vision and pattern recognition applications; however, their adoption in the computer graphics and geometry processing communities is limited due to the non-Euclidean structure of their data. In this paper, we propose Anisotropic Convolutional Neural Network (ACNN), a generalization of classical CNNs to non-Euclidean domains, where classical convolutions are replaced by projections over a set of oriented anisotropic diffusion kernels. We use ACNNs to effectively learn intrinsic dense correspondences between deformable shapes, a fundamental problem in geometry processing, arising in a wide variety of applications. We tested ACNNs performance in challenging settings, achieving state-of-the-art results on recent correspondence benchmarks.

Conference paper

Kovnatsky A, Glashoff K, Bronstein MM, 2016, MADMM: A generic algorithm for non-smooth optimization on manifolds, Pages: 680-696, ISSN: 0302-9743

© Springer International Publishing AG 2016. Numerous problems in computer vision, pattern recognition, and machine learning are formulated as optimization with manifold constraints. In this paper, we propose the Manifold Alternating Directions Method of Multipliers (MADMM), an extension of the classical ADMM scheme for manifold-constrained non-smooth optimization problems. To our knowledge, MADMM is the first generic non-smooth manifold optimization method. We showcase our method on several challenging problems in dimensionality reduction, non-rigid correspondence, multi-modal clustering, and multidimensional scaling.

Conference paper

Boscaini D, Masci J, Rodolà E, Bronstein Met al., 2016, Learning shape correspondence with anisotropic convolutional neural networks, Pages: 3189-3197

Conference paper

Eynard D, Kovnatsky A, Bronstein MM, Glashoff K, Bronstein AMet al., 2015, Multimodal Manifold Analysis by Simultaneous Diagonalization of Laplacians, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol: 37, Pages: 2505-2517, ISSN: 0162-8828

© 2015 IEEE. We construct an extension of spectral and diffusion geometry to multiple modalities through simultaneous diagonalization of Laplacian matrices. This naturally extends classical data analysis tools based on spectral geometry, such as diffusion maps and spectral clustering. We provide several synthetic and real examples of manifold learning, object classification, and clustering, showing that the joint spectral geometry better captures the inherent structure of multi-modal data. We also show the relation of many previous approaches for multimodal manifold analysis to our framework.

Journal article

Kovnatsky A, Bronstein MM, Bresson X, Vandergheynst Pet al., 2015, Functional correspondence by matrix completion, Pages: 905-914, ISSN: 1063-6919

© 2015 IEEE. In this paper, we consider the problem of finding dense intrinsic correspondence between manifolds using the recently introduced functional framework. We pose the functional correspondence problem as matrix completion with manifold geometric structure and inducing functional localization with the L1 norm. We discuss efficient numerical procedures for the solution of our problem. Our method compares favorably to the accuracy of state-of-the-art correspondence algorithms on non-rigid shape matching benchmarks, and is especially advantageous in settings when only scarce data is available.

Conference paper

Boscaini D, Masci J, Melzi S, Bronstein MM, Castellani U, Vandergheynst P, Boscaini D, Masci J, Melzi S, Bronstein MM, Castellani U, Vandergheynst Pet al., 2015, Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks, Computer Graphics Forum, Vol: 34, Pages: 13-23, ISSN: 0167-7055

© 2015 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd. In this paper, we propose a generalization of convolutional neural networks (CNN) to non-Euclidean domains for the analysis of deformable shapes. Our construction is based on localized frequency analysis (a generalization of the windowed Fourier transform to manifolds) that is used to extract the local behavior of some dense intrinsic descriptor, roughly acting as an analogy to patches in images. The resulting local frequency representations are then passed through a bank of filters whose coefficient are determined by a learning procedure minimizing a task-specific cost. Our approach generalizes several previous methods such as HKS, WKS, spectral CNN, and GPS embeddings. Experimental results show that the proposed approach allows learning class-specific shape descriptors significantly outperforming recent state-of-the-art methods on standard benchmarks.

Journal article

Boscaini D, Eynard D, Kourounis D, Bronstein MMet al., 2015, Shape-from-Operator: Recovering Shapes from Intrinsic Operators, Pages: 265-274, ISSN: 0167-7055

© 2015 The Author(s) Computer Graphics Forum © 2015 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd. We formulate the problem of shape-from-operator (SfO), recovering an embedding of a mesh from intrinsic operators defined through the discrete metric (edge lengths). Particularly interesting instances of our SfO problem include: shape-from-Laplacian, allowing to transfer style between shapes; shape-from-difference operator, used to synthesize shape analogies; and shape-from-eigenvectors, allowing to generate 'intrinsic averages' of shape collections. Numerically, we approach the SfO problem by splitting it into two optimization sub-problems: metric-from-operator (reconstruction of the discrete metric from the intrinsic operator) and embedding-from-metric (finding a shape embedding that would realize a given metric, a setting of the multidimensional scaling problem). We study numerical properties of our problem, exemplify it on several applications, and discuss its imitations.

Conference paper

Shahid N, Kalofolias V, Bresson X, Bronstein M, Vandergheynst Pet al., 2015, Robust principal component analysis on graphs, Pages: 2812-2820, ISSN: 1550-5499

© 2015 IEEE. Principal Component Analysis (PCA) is the most widely used tool for linear dimensionality reduction and clustering. Still it is highly sensitive to outliers and does not scale well with respect to the number of data samples. Robust PCA solves the first issue with a sparse penalty term. The second issue can be handled with the matrix factorization model, which is however non-convex. Besides, PCA based clustering can also be enhanced by using a graph of data similarity. In this article, we introduce a new model called 'Robust PCA on Graphs' which incorporates spectral graph regularization into the Robust PCA framework. Our proposed model benefits from 1) the robustness of principal components to occlusions and missing values, 2) enhanced low-rank recovery, 3) improved clustering property due to the graph smoothness assumption on the low-rank matrix, and 4) convexity of the resulting optimization problem. Extensive experiments on 8 benchmark, 3 video and 2 artificial datasets with corruptions clearly reveal that our model outperforms 10 other state-of-the-art models in its clustering and low-rank recovery tasks.

Conference paper

Masci J, Boscaini D, Bronstein MM, Vandergheynst Pet al., 2015, Geodesic Convolutional Neural Networks on Riemannian Manifolds, Pages: 832-840, ISSN: 1550-5499

© 2015 IEEE. Feature descriptors play a crucial role in a wide range of geometry analysis and processing applications, including shape correspondence, retrieval, and segmentation. In this paper, we introduce Geodesic Convolutional Neural Networks (GCNN), a generalization of the convolutional neural networks (CNN) paradigm to non-Euclidean manifolds. Our construction is based on a local geodesic system of polar coordinates to extract "patches", which are then passed through a cascade of filters and linear and non-linear operators. The coefficients of the filters and linear combination weights are optimization variables that are learned to minimize a task-specific cost function. We use ShapeNet to learn invariant shape features, allowing to achieve state-of-The-Art performance in problems such as shape description, retrieval, and correspondence.

Conference paper

Svoboda J, Bronstein MM, Drahansky M, 2015, Contactless biometric hand geometry recognition using a low-cost 3D camera, Pages: 452-457

© 2015 IEEE. In the past decade, the interest in using 3D data for biometric person authentication has increased significantly, propelled by the availability of affordable 3D sensors. The adoption of 3D features has been especially successful in face recognition applications, leading to several commercial 3D face recognition products. In other biometric modalities such as hand recognition, several studies have shown the potential advantage of using 3D geometric information, however, no commercial-grade systems are currently available. In this paper, we present a contactless 3D hand recognition system based on the novel Intel RealSense camera, the first mass-produced embeddable 3D sensor. The small form factor and low cost make this sensor especially appealing for commercial biometric applications, however, they come at the price of lower resolution compared to more expensive 3D scanners used in previous research. We analyze the robustness of several existing 2D and 3D features that can be extracted from the images captured by the RealSense camera and study the use of metric learning for their fusion.

Conference paper

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=2&respub-action=search.html