Results 1  10
of
42
Shape matching and object recognition using low distortion correspondence
 In CVPR
, 2005
"... We approach recognition in the framework of deformable shape matching, relying on a new algorithm for finding correspondences between feature points. This algorithm sets up correspondence as an integer quadratic programming problem, where the cost function has terms based on similarity of correspond ..."
Abstract

Cited by 292 (13 self)
 Add to MetaCart
We approach recognition in the framework of deformable shape matching, relying on a new algorithm for finding correspondences between feature points. This algorithm sets up correspondence as an integer quadratic programming problem, where the cost function has terms based on similarity of corresponding geometric blur point descriptors as well as the geometric distortion between pairs of corresponding feature points. The algorithm handles outliers, and thus enables matching of exemplars to query images in the presence of occlusion and clutter. Given the correspondences, we estimate an aligning transform, typically a regularized thin plate spline, resulting in a dense correspondence between the two shapes. Object recognition is then handled in a nearest neighbor framework where the distance between exemplar and query is the matching cost between corresponding points. We show results on two datasets. One is the Caltech 101 dataset (FeiFei, Fergus and Perona), an extremely challenging dataset with large intraclass variation. Our approach yields a 48 % correct classification rate, compared to FeiFei et al’s 16%. We also show results for localizing frontal and profile faces that are comparable to special purpose approaches tuned to faces. 1.
A spectral technique for correspondence problems using pairwise constraints
 In ICCV
, 2005
"... We present an efficient spectral method for finding consistent correspondences between two sets of features. We build the adjacency matrix M of a graph whose nodes represent the potential correspondences and the weights on the links represent pairwise agreements between potential correspondences. Co ..."
Abstract

Cited by 131 (9 self)
 Add to MetaCart
We present an efficient spectral method for finding consistent correspondences between two sets of features. We build the adjacency matrix M of a graph whose nodes represent the potential correspondences and the weights on the links represent pairwise agreements between potential correspondences. Correct assignments are likely to establish links among each other and thus form a strongly connected cluster. Incorrect correspondences establish links with the other correspondences only accidentally, so they are unlikely to belong to strongly connected clusters. We recover the correct assignments based on how strongly they belong to the main cluster of M, by using the principal eigenvector of M and imposing the mapping constraints required by the overall correspondence mapping (onetoone or onetomany). The experimental evaluation shows that our method is robust to outliers, accurate in terms of matching rate, while being much faster than existing methods. 1.
Recovering human body configurations using pairwise constraints between parts
 ICCV
"... The goal of this work is to recover human body configurations from static images. Without assuming a priori knowledge of scale, pose or appearance, this problem is extremely challenging and demands the use of all possible sources of information. We develop a framework which can incorporate arbitrary ..."
Abstract

Cited by 71 (6 self)
 Add to MetaCart
The goal of this work is to recover human body configurations from static images. Without assuming a priori knowledge of scale, pose or appearance, this problem is extremely challenging and demands the use of all possible sources of information. We develop a framework which can incorporate arbitrary pairwise constraints between body parts, such as scale compatibility, relative position, symmetry of clothing and smooth contour connections between parts. We detect candidate body parts from bottomup using parallelism, and use various pairwise configuration constraints to assemble them together into body configurations. To find the most probable configuration, we solve an Integer Quadratic Programming problem with a standard technique using linear approximations. Approximate IQP allows us to incorporate much more information than the traditional dynamic programming and remains computationally efficient. 15 handlabeled images are used to train the lowlevel part detector and learn the pairwise constraints. We show test results on a variety of images. 1.
Feature Correspondence via Graph Matching: Models and Global Optimization
"... Abstract. In this paper we present a new approach for establishing correspondences between sparse image features related by an unknown nonrigid mapping and corrupted by clutter and occlusion, such as points extracted from a pair of images containing a human figure in distinct poses. We formulate th ..."
Abstract

Cited by 60 (1 self)
 Add to MetaCart
Abstract. In this paper we present a new approach for establishing correspondences between sparse image features related by an unknown nonrigid mapping and corrupted by clutter and occlusion, such as points extracted from a pair of images containing a human figure in distinct poses. We formulate this matching task as an energy minimization problem by defining a complex objective function of the appearance and the spatial arrangement of the features. Optimization of this energy is an instance of graph matching, which is in general a NPhard problem. We describe a novel graph matching optimization technique, which we refer to as dual decomposition (DD), and demonstrate on a variety of examples that this method outperforms existing graph matching algorithms. In the majority of our examples DD is able to find the global minimum within a minute. The ability to globally optimize the objective allows us to accurately learn the parameters of our matching model from training examples. We show on several matching tasks that our learned model yields results superior to those of stateoftheart methods. 1
A tensorbased algorithm for highorder graph matching
 In CVPR
, 2009
"... Abstract—This paper addresses the problem of establishing correspondences between two sets of visual features using higherorder constraints instead of the unary or pairwise ones used in classical methods. Concretely, the corresponding hypergraph matching problem is formulated as the maximization of ..."
Abstract

Cited by 37 (2 self)
 Add to MetaCart
Abstract—This paper addresses the problem of establishing correspondences between two sets of visual features using higherorder constraints instead of the unary or pairwise ones used in classical methods. Concretely, the corresponding hypergraph matching problem is formulated as the maximization of a multilinear objective function over all permutations of the features. This function is defined by a tensor representing the affinity between feature tuples. It is maximized using a generalization of spectral techniques where a relaxed problem is first solved by a multidimensional power method, and the solution is then projected onto the closest assignment matrix. The proposed approach has been implemented, and it is compared to stateoftheart algorithms on both synthetic and real data.
A Survey on Shape Correspondence
, 2011
"... We review methods designed to compute correspondences between geometric shapes represented by triangle meshes, contours, or point sets. This survey is motivated in part by recent developments in spacetime registration, where one seeks a correspondence between nonrigid and timevarying surfaces, an ..."
Abstract

Cited by 28 (6 self)
 Add to MetaCart
We review methods designed to compute correspondences between geometric shapes represented by triangle meshes, contours, or point sets. This survey is motivated in part by recent developments in spacetime registration, where one seeks a correspondence between nonrigid and timevarying surfaces, and semantic shape analysis, which underlines a recent trend to incorporate shape understanding into the analysis pipeline. Establishing a meaningful correspondence between shapes is often difficult since it generally requires an understanding of the structure of the shapes at both the local and global levels, and sometimes the functionality of the shape parts as well. Despite its inherent complexity, shape correspondence is a recurrent problem and an essential component of numerous geometry processing applications. In this survey, we discuss the different forms of the correspondence problem and review the main solution methods, aided by several classification criteria arising from the problem definition. The main categories of classification are defined in terms of the input and output representation, objective function, and solution approach. We conclude the survey by discussing open problems and future perspectives.
An Integer Projected Fixed Point Method for Graph Matching and MAP Inference
"... Graph matching and MAP inference are essential problems in computer vision and machine learning. We introduce a novel algorithm that can accommodate both problems and solve them efficiently. Recent graph matching algorithms are based on a general quadratic programming formulation, which takes in con ..."
Abstract

Cited by 19 (3 self)
 Add to MetaCart
Graph matching and MAP inference are essential problems in computer vision and machine learning. We introduce a novel algorithm that can accommodate both problems and solve them efficiently. Recent graph matching algorithms are based on a general quadratic programming formulation, which takes in consideration both unary and secondorder terms reflecting the similarities in local appearance as well as in the pairwise geometric relationships between the matched features. This problem is NPhard, therefore most algorithms find approximate solutions by relaxing the original problem. They find the optimal continuous solution of the modified problem, ignoring during optimization the original discrete constraints. Then the continuous solution is quickly binarized at the end, but very little attention is put into this final discretization step. In this paper we argue that the stage in which a discrete solution is found is crucial for good performance. We propose an efficient algorithm, with climbing and convergence properties, that optimizes in the discrete domain the quadratic score, and it gives excellent results either by itself or by starting from the solution returned by any graph matching algorithm. In practice it outperforms stateorthe art graph matching algorithms and it also significantly improves their performance if used in combination. When applied to MAP inference, the algorithm is a parallel extension of Iterated Conditional Modes (ICM) with climbing and convergence properties that make it a compelling alternative to the sequential ICM. In our experiments on MAP inference our algorithm proved its effectiveness by significantly outperforming [13], ICM and MaxProduct Belief Propagation. 1
Robust shape tracking in the presence of cluttered background on image processing
 in Proc. IEEE Int. Conf. Image Processing
, 2000
"... Abstract—Many objecttracking algorithms are based on lowlevel features detected in the image. Typically, the object shape and position are estimated to fit the observed features. Unfortunately, image analysis methods often produce invalid features (outliers) which do not belong to the object bounda ..."
Abstract

Cited by 17 (8 self)
 Add to MetaCart
Abstract—Many objecttracking algorithms are based on lowlevel features detected in the image. Typically, the object shape and position are estimated to fit the observed features. Unfortunately, image analysis methods often produce invalid features (outliers) which do not belong to the object boundary. These features have a strong influence on the shape estimates, leading to meaningless tracking results. This paper proposes a robust tracking algorithm which is able to deal with outliers, inspired in the probabilistic data association filter proposed in the context of point tracking. The algorithm is based on two key concepts. First, middle level features (strokes) are used instead of lowlevel ones (edge points). Second, two labels (valid/invalid) are considered for each stroke. Since the stroke labels are unknown all labeling sequences are considered and a probability (confidence degree) is assigned to each of them. In this way, all the strokes contribute to track the moving object but with different weights. This allows a robust performance of the tracker in the presence of outliers. Experimental tests are provided to assess the performance of the proposed algorithm in lip and gesture tracking and surveillance applications. Index Terms—Data association, deformable contours, object tracking, robust filtering, shape analysis. I.
Shape Matching and Object Recognition
, 2005
"... Abstract. We approach recognition in the framework of deformable shape matching, relying on a new algorithm for finding correspondences between feature points. This algorithm sets up correspondence as an integer quadratic programming problem, where the cost function has terms based on similarity of ..."
Abstract

Cited by 15 (2 self)
 Add to MetaCart
Abstract. We approach recognition in the framework of deformable shape matching, relying on a new algorithm for finding correspondences between feature points. This algorithm sets up correspondence as an integer quadratic programming problem, where the cost function has terms based on similarity of corresponding geometric blur point descriptors as well as the geometric distortion between pairs of corresponding feature points. The algorithm handles outliers, and thus enables matching of exemplars to query images in the presence of occlusion and clutter. Given the correspondences, we estimate an aligning transform, typically a regularized thin plate spline, resulting in a dense correspondence between the two shapes. Object recognition is handled in a nearest neighbor framework where the distance between exemplar and query is the matching cost between corresponding points. We show results on two datasets. One is the Caltech 101 dataset (Li, Fergus and Perona), a challenging dataset with large intraclass variation. Our approach yields a 45 % correct classification rate in addition to localization. We also show results for localizing frontal and profile faces that are comparable to special purpose approaches tuned to faces. 1
Matching of objects nodal points improvement using optimization
 Inverse Problems in Science and Engineering
, 2004
"... The main objective of this work was to improve a previously developed object matching methodology. This overall methodology includes: a modeling phase; followed by a modal analysis; the construction of a matrix that relates both sets of objects points; and the matching phase. The previously implemen ..."
Abstract

Cited by 13 (11 self)
 Add to MetaCart
The main objective of this work was to improve a previously developed object matching methodology. This overall methodology includes: a modeling phase; followed by a modal analysis; the construction of a matrix that relates both sets of objects points; and the matching phase. The previously implemented matching phase is based on a local search; with this solution the relation between objects nodes (points) are not considered. To overcome this, we implemented a new matching solution, using optimization techniques, based on a global search. This solution is compared with the previous one allowing the verification of the results improvement. The local and the global search methods used in this work allow only matches of the usual type “one to one”. However, there are situations when this type of matches is not the most adequate, since it can imply loss of information. To avoid this problem, we developed a new algorithm applicable to contour objects that finds satisfactory matches of type “one to many ” or viceversa.