Results 1  10
of
13
Selecting Canonical Views for ViewBased 3D Object Recognition
, 2004
"... Given a collection of sets of 2D views of 3D objects and a similarity measure between them, we present a method for summarizing the sets using a small subset called a bounded canonical set (BCS), whose members best represent the members of the original set. This means that members of the BCS are a ..."
Abstract

Cited by 24 (2 self)
 Add to MetaCart
Given a collection of sets of 2D views of 3D objects and a similarity measure between them, we present a method for summarizing the sets using a small subset called a bounded canonical set (BCS), whose members best represent the members of the original set. This means that members of the BCS are as dissimilar from each other as possible, while at the same time being as similar as possible to the nonBCS members. This paper will extend our earlier work on computing canonical sets [2] in several ways: by omitting the need for a multiobjective optimization, by allowing the imposition of cardinality constraints, and by introducing a total similarity function. We evaluate the applicability of BCS to view selection in a viewbased object recognition environment.
Scenariographer: A tool for reverse engineering class usage scenarios from method invocation sequences
 IN ICSM
, 2005
"... ..."
(Show Context)
Stable bounded canonical sets and image matching
 IN ENERGY MINIMIZATION METHODS IN COMPUTER VISION AND PATTERN RECOGNITION, EMMCVPR 2005
, 2005
"... A common approach to the image matching problem is representing images as sets of features in some feature space followed by establishing correspondences among the features. Previous work by Huttenlocher and Ullman [1] shows how a similarity transformation rotation, translation, and scaling betw ..."
Abstract

Cited by 6 (5 self)
 Add to MetaCart
(Show Context)
A common approach to the image matching problem is representing images as sets of features in some feature space followed by establishing correspondences among the features. Previous work by Huttenlocher and Ullman [1] shows how a similarity transformation rotation, translation, and scaling between two images may be determined assuming that three corresponding image points are known. While robust, such methods suffer from computational inefficiencies for general feature sets. We describe a method whereby the feature sets may be summarized using the Stable Bounded Canonical Set (SBCS), thus allowing the efficient computation of point correspondences between large feature sets. We use a notion of stability to influence the set summarization such that stable image features are preferred.
Discovering shape classes using tree editdistance and pairwise clustering
 IJCV
, 2007
"... This paper describes work aimed at the unsupervised learning of shapeclasses from shock trees. We commence by considering how to compute the edit distance between weighted trees. We show how to transform the tree edit distance problem into a series of maximum weight clique problems, and show how ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
This paper describes work aimed at the unsupervised learning of shapeclasses from shock trees. We commence by considering how to compute the edit distance between weighted trees. We show how to transform the tree edit distance problem into a series of maximum weight clique problems, and show how to use relaxation labeling to find an approximate solution. This allows us to compute a set of pairwise distances between graphstructures. We show how the edit distances can be used to compute a matrix of pairwise affinities using χ2 statistics. We present a maximum likelihood method for clustering the graphs by iteratively updating the elements of the affinity matrix. This involves interleaved steps for updating the affinity matrix using an eigendecomposition method and updating the cluster membership indicators. We illustrate the new tree clustering framework on shockgraphs extracted from the silhouettes of 2D shapes.
Studying the evolution of software systems using change clusters
 Proceedings of the 14th IEEE International Conference on Program Comprehension
"... In this paper, we present an approach that examines the evolution of code stored in source control repositories. The technique identifies Change Clusters, which can help managers to classify different code change activities as either a software maintenance or a new development. Furthermore, identify ..."
Abstract

Cited by 5 (1 self)
 Add to MetaCart
(Show Context)
In this paper, we present an approach that examines the evolution of code stored in source control repositories. The technique identifies Change Clusters, which can help managers to classify different code change activities as either a software maintenance or a new development. Furthermore, identifying the variations in Change Clusters over time exposes trends in the development of a software system. We present a case study that uses a sequence of Change Clusters to track the evolution of the PostgreSQL software project. Our case study demonstrates that our technique reveals interesting patterns about the progress of code development within each release of PostgreSQL. We show that the increase in the number of clusters not only identifies the areas where development has occurred, but also reflects the amount of structural change in code. We also compare how the Change Clusters vary over time in order to make generalizations about the focus of development. 1
Combining Different Types of Scale Space Interest Points Using Canonical Sets
, 2007
"... Scale space interest points capture important photometric and deep structure information of an image. The information content of such points can be made explicit using image reconstruction. In this paper we will consider the problem of combining multiple types of interest points used for image rec ..."
Abstract
 Add to MetaCart
Scale space interest points capture important photometric and deep structure information of an image. The information content of such points can be made explicit using image reconstruction. In this paper we will consider the problem of combining multiple types of interest points used for image reconstruction. It is shown that ordering the complete set of points by differential (quadratic) TVnorm (which works for single feature types) does not yield optimal results for combined point sets. The paper presents a method to solve this problem using canonical sets of scale space features. Qualitative and quantitative analysis show improved performance over simple ordering of points using the TVnorm.
Discovering Shape Classes using Tree EditDistance and Pairwise Clustering
, 2006
"... This paper describes work aimed at the unsupervised learning of shapeclasses from shock trees. We commence by considering how to compute the edit distance between weighted trees. We show how to transform the tree edit distance problem into a series of maximum weight clique problems, and show how t ..."
Abstract
 Add to MetaCart
This paper describes work aimed at the unsupervised learning of shapeclasses from shock trees. We commence by considering how to compute the edit distance between weighted trees. We show how to transform the tree edit distance problem into a series of maximum weight clique problems, and show how to use relaxation labeling to find an approximate solution. This allows us to compute a set of pairwise distances between graphstructures. We show how the edit distances can be used to compute a matrix of pairwise affinities using χ 2 statistics. We present a maximum likelihood method for clustering the graphs by iteratively updating the elements of the affinity matrix. This involves interleaved steps for updating the affinity matrix using an eigendecomposition method and updating the cluster membership indicators. We illustrate the new tree clustering framework on shockgraphs extracted from the silhouettes of 2D shapes.
A Visualization Tool for fMRI Data Mining
"... fMRI is an imaging technique that is used to understand brain functionality. Scans are taken at intervals as a patient performs some mental tasks, resulting in hundreds of datasets. It is an increasingly popular technique in fields ranging from medicine, psychology or even marketing and economics. H ..."
Abstract
 Add to MetaCart
(Show Context)
fMRI is an imaging technique that is used to understand brain functionality. Scans are taken at intervals as a patient performs some mental tasks, resulting in hundreds of datasets. It is an increasingly popular technique in fields ranging from medicine, psychology or even marketing and economics. However, these images tend to be noisy and new packages are constantly being developed to analyze and filter these large datasets. Because of the large data size and many analysis parameters, comparisons between results or between experiments are difficult. We present a visualization tool that allows interactive comparison of different analyzed datasets. Such analyzed datasets can be results of different analytic methods used in fMRI analysis, on data from one or more ii subjects and/or one or more experiments. We treat every analysis result as a functional clustering of voxels mapped into brain space and employ visualization techniques to allow the user to interactively explore the similarity and differences between the different datasets. This can provide valuable insight into the data or the analysis methodologies being studied. Thus, the tool can be used as a visualization interface of a data mining engine and could also support a "querybyexample " approach to fMRI data retrieval.