Results 1  10
of
51
Using Discriminant Eigenfeatures for Image Retrieval
, 1996
"... This paper describes the automatic selection of features from an image training set using the theories of multidimensional linear discriminant analysis and the associated optimal linear projection. We demonstrate the effectiveness of these Most Discriminating Features for viewbased class retrieval ..."
Abstract

Cited by 399 (14 self)
 Add to MetaCart
This paper describes the automatic selection of features from an image training set using the theories of multidimensional linear discriminant analysis and the associated optimal linear projection. We demonstrate the effectiveness of these Most Discriminating Features for viewbased class retrieval from a large database of widely varying realworld objects presented as "wellframed" views, and compare it with that of the principal component analysis.
Shock Graphs and Shape Matching
, 1998
"... We have been developing a theory for the generic representation of 2D shape, where structural descriptions are derived from the shocks (singularities) of a curve evolution process, acting on bounding contours. We now apply the theory to the problem of shape matching. The shocks are organized into a ..."
Abstract

Cited by 213 (34 self)
 Add to MetaCart
We have been developing a theory for the generic representation of 2D shape, where structural descriptions are derived from the shocks (singularities) of a curve evolution process, acting on bounding contours. We now apply the theory to the problem of shape matching. The shocks are organized into a directed, acyclic shock graph, and complexity is managed by attending to the most significant (central) shape components first. The space of all such graphs is highly structured and can be characterized by the rules of a shock graph grammar. The grammar permits a reduction of a shock graph to a unique rooted shock tree. We introduce a novel tree matching algorithm which finds the best set of corresponding nodes between two shock trees in polynomial time. Using a diverse database of shapes, we demonstrate our system's performance under articulation, occlusion, and changes in viewpoint. Keywords: shape representation; shape matching; shock graph; shock graph grammar; subgraph isomorphism. 1 I...
Multidimensional indexing for recognizing visual shapes
 PAMI
, 1994
"... AbstractThis paper introduces an analytical framework for studying some properties of model acquisition and recognition techniques based on indexing. The goal is to demonstrate that several problems previously associated with the approach can be attributed to the low dimensionality of invariants us ..."
Abstract

Cited by 81 (0 self)
 Add to MetaCart
AbstractThis paper introduces an analytical framework for studying some properties of model acquisition and recognition techniques based on indexing. The goal is to demonstrate that several problems previously associated with the approach can be attributed to the low dimensionality of invariants used. These include limited index selectivity, excessive accumulation of votes in the lookup table buckets, and excessive sensitivity to quantization parameters. Theoretical results demonstrate that using highdimensional, highly descriptive global invariants produces better results in terms of accuracy, false positive suppression, and computation time. A practical example of highdimensional global invariants is introduced and used to implement a 2D shape acquisitionhecognition system. The acquisitiodrecognition system is based on a twostep table lookup mechanism. First, local curve descriptors are obtained by correlating image contour information at short range. Then, sevendimensional global invariants are computed by correlating triplets of local curve descriptors at longer range. This experimental system is meant to illustrate the behavior of a highdimensional indexing scheme. Indeed, its performance shows good agreement with the analytical model with respect to database size, fault tolerance, and recognition speed. Model acquisition time is linear to cubic in the number of object features. Object recognition time is constant to linear in the number of models in the database and linear to cubic in the number of features in the image. The system has been tested extensively, with more than 250 arbitrary shapes in the database. Unsupervised shape and subpart acquisition is demonstrated. I.
Computing Exact Aspect Graphs of Curved Objects: Algebraic Surfaces
"... This paper presents an algorithm for computing the exact aspect graph of an opaque solid bounded by a smooth algebraic surface and observed under orthographic projection. The algorithm uses curve tracing, cell decomposition, and ray tracing to construct the regions of the view sphere delineated by ..."
Abstract

Cited by 81 (10 self)
 Add to MetaCart
This paper presents an algorithm for computing the exact aspect graph of an opaque solid bounded by a smooth algebraic surface and observed under orthographic projection. The algorithm uses curve tracing, cell decomposition, and ray tracing to construct the regions of the view sphere delineated by visual events. It has been fully implemented, and examples are presented.
ViewBased Object Recognition Using Saliency Maps
, 1998
"... We introduce a novel viewbased object representation, called the saliency map graph (SMG), which captures the salient regions of an object view at multiple scales using a wavelet transform. This compact representation is highly invariant to translation, rotation (image and depth), and scaling, and ..."
Abstract

Cited by 49 (9 self)
 Add to MetaCart
We introduce a novel viewbased object representation, called the saliency map graph (SMG), which captures the salient regions of an object view at multiple scales using a wavelet transform. This compact representation is highly invariant to translation, rotation (image and depth), and scaling, and offers the locality of representation required for occluded object recognition. To compare two saliency map graphs, we introduce two graph similarity algorithms. The first computes the topological similarity between two SMG's, providing a coarselevel matching of two graphs. The second computes the geometrical similarity between two SMG's, providing a finelevel matching of two graphs. We test and compare these two algorithms on a large database of model object views.
Hierarchical Discriminant Analysis for Image Retrieval
 IEEE Trans. PAMI
, 1999
"... Abstract—A selforganizing framework for object recognition is described. We describe a hierarchical database structure for image retrieval. The SelfOrganizing Hierarchical Optimal Subspace Learning and Inference Framework (SHOSLIF) system uses the theories of optimal linear projection for automati ..."
Abstract

Cited by 48 (4 self)
 Add to MetaCart
Abstract—A selforganizing framework for object recognition is described. We describe a hierarchical database structure for image retrieval. The SelfOrganizing Hierarchical Optimal Subspace Learning and Inference Framework (SHOSLIF) system uses the theories of optimal linear projection for automatic optimal feature derivation and a hierarchical structure to achieve a logarithmic retrieval complexity. A SpaceTessellation Tree is automatically generated using the Most Expressive Features (MEFs) and the Most Discriminating Features (MDFs) at each level of the tree. The major characteristics of the proposed hierarchical discriminant analysis include: 1) avoiding the limitation of global linear features (hyperplanes as separators) by deriving a recursively betterfitted set of features for each of the recursively subdivided sets of training samples; 2) generating a smaller tree whose cell boundaries separate the samples along the class boundaries better than the principal component analysis, thereby giving a better generalization capability (i.e., better recognition rate in a disjoint test); 3) accelerating the retrieval using a tree structure for data pruning, utilizing a different set of discriminant features at each level of the tree. We allow for perturbations in the size and position of objects in the images through learning. We demonstrate the technique on a large image database of widely varying realworld objects taken in natural settings, and show the applicability of the approach for variability in position, size, and 3D orientation. This paper concentrates on the hierarchical partitioning of the feature spaces. Index Terms—Principal component analysis, discriminant analysis, hierarchical image database, image retrieval, tessellation, partitioning, object recognition, face recognition, complexity with large image databases.
Hierarchical discriminant regression
 IEEE Trans. Pattern Anal. Mach. Intell
, 2000
"... AbstractÐThe main motivation of this paper is to propose a new classification and regression method for challenging highdimensional data. The proposed new technique casts classification problems (class labels as output) and regression problems (numeric values as output) into a unified regression pro ..."
Abstract

Cited by 46 (24 self)
 Add to MetaCart
AbstractÐThe main motivation of this paper is to propose a new classification and regression method for challenging highdimensional data. The proposed new technique casts classification problems (class labels as output) and regression problems (numeric values as output) into a unified regression problem. This unified view enables classification problems to use numeric information in the output space that is available for regression problems but are traditionally not readily available for classification problemsÐdistance metric among clustered class labels for coarse and fine classifications. A doubly clustered subspacebased hierarchical discriminating regression (HDR) method is proposed in this work. The major characteristics include: 1) Clustering is performed in both output space and input space at each internal node, termed ªdoubly clustered.º Clustering in the output space provides virtual labels for computing clusters in the input space. 2) Discriminants in the input space are automatically derived from the clusters in the input space. These discriminants span the discriminating subspace at each internal node of the tree. 3) A hierarchical probability distribution model is applied to the resulting discriminating subspace at each internal node. This realizes a coarsetofine approximation of probability distribution of the input samples, in the hierarchical discriminating subspaces. No global distribution models are assumed. 4) To relax the per class sample requirement of traditional discriminant analysis techniques, a samplesize dependent negativeloglikelihood (NLL) is introduced. This new technique is designed for automatically dealing with smallsample applications, largesample applications, and unbalancedsample applications. 5) The execution of HDR method is fast, due to the empirical logarithmic time complexity of the HDR algorithm. Although the method is applicable to any data, we report the experimental results for three types of data: synthetic data for examining the nearoptimal performance, large raw faceimage data bases, and traditional databases with manually selected features along with a comparison with some major existing methods, such as CART,
CADBased Computer Vision: From CAD Models to Relational Graphs
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 1991
"... 3D object recognition is a difficult and yet an important problem in computer vision. A 3D object recognition system has two major componenb, object modeling (or representation) and matching stored representations to those derived from the sensed image. In this paper, we focus on the topic of model ..."
Abstract

Cited by 45 (2 self)
 Add to MetaCart
3D object recognition is a difficult and yet an important problem in computer vision. A 3D object recognition system has two major componenb, object modeling (or representation) and matching stored representations to those derived from the sensed image. In this paper, we focus on the topic of modelbuildingfor 3D objecb. Most existing 3D object recognition systems construct models either manually, or by learning from multiple images of an object. Both these approaches have not been very satisfactory, particularly in designing object recognition systems which can handle a large number of objects. Recent interest in integrating mechanical CAD systems and vision systems has led to adaptation of preexisting CAD models of objects for recognition. If a solid model of an object to be recognized is already available in a manufacturing database, then we should be able to infer automatically a model appropriate for vision tasks Lom the manufacturing model. We have developed such a system which uaes 3D object descriptions created on a commercial CAD system and expressed in the industrystandard IGES form, and performs geometric inferencing to obtain a relational graph representation of the object which can be stored in a database of models for object recognition. Details of the IGES standard, the geometric inference engine, and some formal properties of 3D models are discussed. We believe that a system like ours is needed to efficiently create a large database (more than 100 objects) of 3D models to evaluate matching strategies. 1
Retrieving articulated 3D models using medial surfaces
, 2008
"... We consider the use of medial surfaces to represent symmetries of 3D objects. This allows for a qualitative abstraction based on a directed acyclic graph of components and also a degree of invariance to a variety of transformations including the articulation of parts. We demonstrate the use of this ..."
Abstract

Cited by 39 (3 self)
 Add to MetaCart
We consider the use of medial surfaces to represent symmetries of 3D objects. This allows for a qualitative abstraction based on a directed acyclic graph of components and also a degree of invariance to a variety of transformations including the articulation of parts. We demonstrate the use of this representation for 3D object model retrieval. Our formulation uses the geometric information
A similaritybased aspectgraph approach to 3d object recognition
 International Journal of Computer Vision
, 2004
"... Abstract. This paper describes a viewbased method for recognizing 3D objects from 2D images. We employ an aspectgraph structure, where the aspects are not based on the singularities of visual mapping but are instead formed using a notion of similarity between views. Specifically, the viewing spher ..."
Abstract

Cited by 25 (0 self)
 Add to MetaCart
Abstract. This paper describes a viewbased method for recognizing 3D objects from 2D images. We employ an aspectgraph structure, where the aspects are not based on the singularities of visual mapping but are instead formed using a notion of similarity between views. Specifically, the viewing sphere is endowed with a metric of dissimilarity for each pair of views and the problem of aspect generation is viewed as a ”segmentation ” of the viewing sphere into homogeneous regions. The viewing sphere is sampled at regular (5 degree) intervals and an iterative procedure is used to combine views using the metric into aspects with a prototype representing each aspect, in a ”regiongrowing ” regime which stands in contrast to the usual ”edge detection ” styles to computing the aspect graph. The aspect growth is constrained such that two aspects of an object remain distinct under the given similarity metric. Once the database of 3D objects is organized as a set of aspects and prototypes for these aspects for each object, unknown views of database objects are compared with the prototypes and the results are ordered by similarity. We use two similarity metrics for shape, one based on curve matching and the other based on matching shock graphs, which for a database of 64 objects and unknown views of objects for the database give (90.3%, 74.2%, 59.7%) and (95.2%, 69.0%, 57.5%), respectively, for the top three matches; identification based on the top three matches is 98 % and 100%, respectively. The result of indexing unknown views of objects not in the database also produce intuitive matches. We also develop a hierarchical indexing scheme the goal of which is to prune unlikely objects at an early stage to improve the efficiency of indexing, resulting in savings of 35 % at the top level and of 55 % at the next level, cumulatively. 1.