By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 11 • Date Nov 1998

Filter Results

Displaying Results 1 - 13 of 13
  • Shape evolution with structural and topological changes using blending

    Publication Year: 1998, Page(s):1186 - 1205
    Cited by:  Papers (19)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4208 KB)

    This paper describes a framework for the estimation of shape from sparse or incomplete range data. It uses a shape representation called blending, which allows for the geometric combination of shapes into a unified model - selected regions of the component shapes are cut-out and glued together. Estimation of shape by this representation is realized using a physics-based framework, and it also incl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Primitive features by steering, quadrature, and scale

    Publication Year: 1998, Page(s):1161 - 1173
    Cited by:  Papers (13)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1104 KB)

    The impulse response of neurons in the visual cortex of the mammalian brain has been known for some time. How to make use of these as filters has led to many hypotheses. The response of a single filter is ambiguous because the result depends on stimulus type, contrast, position, orientation, and scale. We show that a set of quadrature filters at sparse positions can be constructed so that it is po... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Are multilayer perceptrons adequate for pattern recognition and verification?

    Publication Year: 1998, Page(s):1121 - 1132
    Cited by:  Papers (38)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (404 KB)

    Discusses the ability of multilayer perceptrons (MLPs) to model the probability distribution of data in typical pattern recognition and verification problems. It is proven that multilayer perceptrons with sigmoidal units and a number of hidden units less or equal than the number of inputs are unable to model patterns distributed in typical clusters, since these networks draw open separation surfac... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Graph matching with a dual-step EM algorithm

    Publication Year: 1998, Page(s):1236 - 1253
    Cited by:  Papers (78)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3792 KB)

    This paper describes a new approach to matching geometric structure in 2D point-sets. The novel feature is to unify the tasks of estimating transformation geometry and identifying point-correspondence matches. Unification is realized by constructing a mixture model over the bipartite graph representing the correspondence match and by affecting optimization using the EM algorithm. According to our ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Alternatives to variable duration HMM in handwriting recognition

    Publication Year: 1998, Page(s):1275 - 1280
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (464 KB)

    A successful handwritten word recognition (HWR) system using a variable duration hidden Markov model (VDHMM) and the path discriminant-HMM (PD-HMM) strategy is easy to implement. The central theme of the paper is to show that if the duration statistics are computed, it could be utilized to implement a model-discriminant-HMM (MD-HMM) approach for better experimental results. The paper also describe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust affine structure matching for 3D object recognition

    Publication Year: 1998, Page(s):1265 - 1274
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (584 KB)

    We consider model-based object localization based on local geometric feature matching between the model and the image data. The method is based on geometric constraint analysis, working in transformation space. We present a formal method which guarantees finding all feasible matchings in polynomial time. From there we develop more computationally feasible algorithms based on conservative approxima... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A model of saliency-based visual attention for rapid scene analysis

    Publication Year: 1998, Page(s):1254 - 1259
    Cited by:  Papers (2379)  |  Patents (149)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1940 KB)

    A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. A dynamical neural network then selects attended locations in order of decreasing saliency. The system breaks down the complex problem of scene understanding by rapidly selecting, in a co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Inference of integrated surface, curve and junction descriptions from sparse 3D data

    Publication Year: 1998, Page(s):1206 - 1223
    Cited by:  Papers (30)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1532 KB)

    We address the problem of inferring integrated high-level descriptions such as surfaces, 3D curves, and junctions from a sparse point set. For precise localization, we propose a noniterative cooperative algorithm in which surfaces, curves, and junctions work together. Initial estimates are computed based on the work by Guy and Medioni (1997), where each point in the given sparse and possibly noisy... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic programming generation of curves on brain surfaces

    Publication Year: 1998, Page(s):1260 - 1265
    Cited by:  Papers (49)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (576 KB)

    Dynamic programming algorithms are presented for automated generation of length minimizing geodesics and curves of extremal curvature on the neocortex of the macaque and the visible human. Probabilistic models of curve variation are constructed in terms of the variability in speed, curvature, and torsion in the Frenet representation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intensity- and gradient-based stereo matching using hierarchical Gaussian basis functions

    Publication Year: 1998, Page(s):1143 - 1160
    Cited by:  Papers (31)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (11252 KB)

    We propose a stereo correspondence method by minimizing intensity and gradient errors simultaneously. In contrast to conventional use of image gradients, the gradients are applied in the deformed image space. Although a uniform smoothness constraint is imposed, it is applied only to nonfeature regions. To avoid local minima in the function minimization, we propose to parameterize the disparity fun... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling and classifying symmetries using a multiscale opponent color representation

    Publication Year: 1998, Page(s):1224 - 1235
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2664 KB)

    A new class of multiscale symmetry features provides a useful high-level representation for color texture. These symmetry features are defined within and between the bands of a color image using complex moments computed from the output of a bank of orientation and scale selective filters. We show that these features not only represent symmetry information but are also invariant to rotation, scale,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • RIEVL: recursive induction learning in hand gesture recognition

    Publication Year: 1998, Page(s):1174 - 1185
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (964 KB)

    Presents a recursive inductive learning scheme that is able to acquire hand pose models in the form of disjunctive normal form expressions involving multivalued features. Based on an extended variable-valued logic, our rule-based induction system is able to abstract compact rule sets from any set of feature vectors describing a set of classifications. The rule bases which satisfy the completeness ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian approaches to Gaussian mixture modeling

    Publication Year: 1998, Page(s):1133 - 1142
    Cited by:  Papers (90)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1016 KB)

    A Bayesian-based methodology is presented which automatically penalizes overcomplex models being fitted to unknown data. We show that, with a Gaussian mixture model, the approach is able to select an “optimal” number of components in the model and so partition data sets. The performance of the Bayesian method is compared to other methods of optimal model selection and found to give goo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is published monthly. Its editorial board strives to present most important research results in areas within TPAMI's scope.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
David A. Forsyth
University of Illinois
e-mail: daf@illinois.edu