Results 1  10
of
19
Shape Distributions
 ACM Transactions on Graphics
, 2002
"... this paper, we propose and analyze a method for computing shape signatures for arbitrary (possibly degenerate) 3D polygonal models. The key idea is to represent the signature of an object as a shape distribution sampled from a shape function measuring global geometric properties of an object. The pr ..."
Abstract

Cited by 192 (0 self)
 Add to MetaCart
this paper, we propose and analyze a method for computing shape signatures for arbitrary (possibly degenerate) 3D polygonal models. The key idea is to represent the signature of an object as a shape distribution sampled from a shape function measuring global geometric properties of an object. The primary motivation for this approach is to reduce the shape matching problem to the comparison of probability distributions, which is simpler than traditional shape matching methods that require pose registration, feature correspondence, or model fitting
Matching 3D Models with Shape Distributions
"... Measuring the similarity between 3D shapes is a fundamental problem, with applications in computer vision, molecular biology, computer graphics, and a variety of other fields. A challenging aspect of this problem is to find a suitable shape signature that can be constructed and compared quickly, whi ..."
Abstract

Cited by 172 (7 self)
 Add to MetaCart
Measuring the similarity between 3D shapes is a fundamental problem, with applications in computer vision, molecular biology, computer graphics, and a variety of other fields. A challenging aspect of this problem is to find a suitable shape signature that can be constructed and compared quickly, while still discriminating between similar and dissimilar shapes. In this paper, we propose and analyze a method for computing shape signatures for arbitrary (possibly degenerate) 3D polygonal models. The key idea is to represent the signature of an object as a shape distribution sampled from a shape function measuring global geometric properties of an object. The primary motivation for this approach is to reduce the shape matching problem to the comparison of probability distributions, which is a simpler problem than the comparison of 3D surfaces by traditional shape matching methods that require pose registration, feature correspondence, or model fitting. We find that the dissimilarities be...
Fast pose estimation with parameter sensitive hashing
 In ICCV
, 2003
"... Examplebased methods are effective for parameter estimation problems when the underlying system is simple or the dimensionality of the input is low. For complex and highdimensional problems such as pose estimation, the number of required examples and the computational complexity rapidly become pro ..."
Abstract

Cited by 102 (4 self)
 Add to MetaCart
Examplebased methods are effective for parameter estimation problems when the underlying system is simple or the dimensionality of the input is low. For complex and highdimensional problems such as pose estimation, the number of required examples and the computational complexity rapidly become prohibitively high. We introduce a new algorithm that learns a set of hashing functions that efficiently index examples relevant to a particular estimation task. Our algorithm extends a recently developed method for localitysensitive hashing, which finds approximate neighbors in time sublinear in the number of examples. This method depends critically on the choice of hash functions; we show how to find the set of hash functions that are optimally relevant to a particular estimation problem. Experiments demonstrate that the resulting algorithm, which we call ParameterSensitive Hashing, can rapidly and accurately estimate the articulated pose of human figures from a large database of example images. 1.
The bhattacharyya metric as an absolute similarity measure for frequency coded data
 Kybernetika
, 1997
"... A recurring problem that arises throughout the sciences is that of deciding whether two statistical distributions differ or are consistent currently the chisquared statistic is the most commonly used technique for addressing this problem. This paper explains the drawbacks of the chisquared statis ..."
Abstract

Cited by 52 (4 self)
 Add to MetaCart
A recurring problem that arises throughout the sciences is that of deciding whether two statistical distributions differ or are consistent currently the chisquared statistic is the most commonly used technique for addressing this problem. This paper explains the drawbacks of the chisquared statistic for comparing measurements over large distances in pattern space and suggests that the Bhattacharyya measure can avoid such difficulties. The original interpretation of the Bhattacharyya metric as a geometric similarity measure is reviewed and it is pointed out that this derivation is independent of the use of the Bhattacharyya measure as an upper bound on misclassification in a twoclass problem. The affinity between the Bhattacharyya and Matusita measures is described and we show that the measure is applicable to any distribution of data. We explain that the Bhattacharyya measure is consistent with an assumption of a Poisson generation mechanism for individual measurements in a distribution which is applicable to a frequency (histogram) or probabilistic data set and suggest application of the Bhattacharyya measure to the field of system identification.
Finding Surface Correspondence for Object Recognition and Registration using Pairwise Geometric Histograms
 in Computer VisionECCV'98
"... . Pairwise geometric histograms have been demonstrated as an effective descriptor of arbitrary 2dimensional shape which enable robust and efficient object recognition in complex scenes. In this paper we describe how the approach can be extended to allow the representation and classification of arbi ..."
Abstract

Cited by 41 (2 self)
 Add to MetaCart
. Pairwise geometric histograms have been demonstrated as an effective descriptor of arbitrary 2dimensional shape which enable robust and efficient object recognition in complex scenes. In this paper we describe how the approach can be extended to allow the representation and classification of arbitrary 2 1 2  and 3dimensional surface shape. This novel representation can be used in important vision tasks such as the recognition of objects with complex freeform surfaces and the registration of surfaces for building 3dimensional models from multiple views. We apply this new representation to both of these tasks and present some promising results. 1 Introduction Finding a correspondence between two or more surfaces is a frequently encountered problem in many computer vision tasks. When surface based descriptions are used for object recognition, the hypothesis that a particular object is in a scene is confirmed by finding a good correspondence between scene and model surfaces [6]. W...
Multiresolution Histograms and their Use for Recognition
 IEEE transactions on Pattern Analysis and Machine Intelligence
, 2004
"... Abstractâ€”The histogram of image intensities is used extensively for recognition and for retrieval of images and video from visual databases. A single image histogram, however, suffers from the inability to encode spatial image variation. An obvious way to extend this feature is to compute the histog ..."
Abstract

Cited by 39 (0 self)
 Add to MetaCart
Abstractâ€”The histogram of image intensities is used extensively for recognition and for retrieval of images and video from visual databases. A single image histogram, however, suffers from the inability to encode spatial image variation. An obvious way to extend this feature is to compute the histograms of multiple resolutions of an image to form a multiresolution histogram. The multiresolution histogram shares many desirable properties with the plain histogram including that they are both fast to compute, space efficient, invariant to rigid motions, and robust to noise. In addition, the multiresolution histogram directly encodes spatial information. We describe a simple yet novel matching algorithm based on the multiresolution histogram that uses the differences between histograms of consecutive image resolutions. We evaluate it against five widely used image features. We show that with our simple feature we achieve or exceed the performance obtained with more complicated features. Further, we show our algorithm to be the most efficient and robust.
Languagebased Querying of Image Collections on the Basis of an Extensible Ontology
 IVC
, 2004
"... The design of a specialised query language for content based image retrieval (CBIR) provides a means of addressing many of the problems associated with commonly used query paradigms such as querybyexample and querybysketch. By basing such a language on an extensible ontology which encompasses bo ..."
Abstract

Cited by 17 (1 self)
 Add to MetaCart
The design of a specialised query language for content based image retrieval (CBIR) provides a means of addressing many of the problems associated with commonly used query paradigms such as querybyexample and querybysketch. By basing such a language on an extensible ontology which encompasses both highlevel and lowlevel image properties and relations, one can go a long way towards bridging the semantic gap between user models of saliency and relevance and those employed by a retrieval system.
Line pattern retrieval using relational histograms
 IEEE TRANS. PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 1999
"... This paper presents a new compact shape representation for retrieving linepatterns from large databases. The basic idea is to exploit both geometric attributes and structural information to construct a shape histogram. We realize this goal by computing the Nnearest neighbor graph for the linesse ..."
Abstract

Cited by 16 (4 self)
 Add to MetaCart
This paper presents a new compact shape representation for retrieving linepatterns from large databases. The basic idea is to exploit both geometric attributes and structural information to construct a shape histogram. We realize this goal by computing the Nnearest neighbor graph for the linessegments for each pattern. The edges of the neighborhood graphs are used to gate contributions to a twodimensional pairwise geometric histogram. Shapes are indexed by searching for the linepattern that maximizes the cross correlation of the normalized histogram bincontents. We evaluate the new method on a database containing over 2,500 linepatterns each composed of hundreds of lines.
Relational Histograms for Shape Indexing
, 1998
"... This paper is concerned with the retrieval of images from large databases based on their shape similarity to a query image. Our approach is based on two dimensional histograms that encode both the local and global geometric properties of the shapes. The pairwise attributes are the directed segment r ..."
Abstract

Cited by 15 (6 self)
 Add to MetaCart
This paper is concerned with the retrieval of images from large databases based on their shape similarity to a query image. Our approach is based on two dimensional histograms that encode both the local and global geometric properties of the shapes. The pairwise attributes are the directed segment relative angle and directed relative position. The novelty of the proposed approach is to simultaneously use the relational and structural constraints, derivedfrom an adjacency graph, to gate histogram contributions. We investiguate the retrieval capabilities of the methodfor various queries. We also investigate the robustness of the methodtosegmentation errors. We conclude that a relational histogram of pairwise segment attributes presents a very efficient way of indexing into large databases. The optimal configuration is obtainedwhen the local features are constructed from six neighbouring segments pairs. Moreover, a sensitivity analysis reveals that segmentation errors do not affect the ...
Fuzzy Relational for Distance LargeScale Object Recognition
, 1998
"... This paper presents a new similarity measure for object recognition from large libraries of linepatterns. The measuredraws its inspiration from both the Hausdorff distanceandarecently reported Bayesian consistency measure that has been sucessfully usedforgraphbased correspondence matching. The meas ..."
Abstract

Cited by 8 (4 self)
 Add to MetaCart
This paper presents a new similarity measure for object recognition from large libraries of linepatterns. The measuredraws its inspiration from both the Hausdorff distanceandarecently reported Bayesian consistency measure that has been sucessfully usedforgraphbased correspondence matching. The measure uses robust errorkernels to gauge the similarity of pairwise attribute relations definedontheedges of nearest neighbour graphs. We use the similarity measureina recognition experiment which involves a library of over 1000 linepatterns. A sensitivity study reveals that the methodiscapable of delivering arecognition accuracy of 98%. Acomparative study reveals that the method is most effective when a Gaussian kernel or Huber's robust kernel is used to weight the attribute relations. Moreover, the method consistently outperforms Rucklidge's median Hausdorff distance.