By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 12 • Date Dec. 1998

Filter Results

Displaying Results 1 - 15 of 15
  • Dynamic-scale model construction from range imagery

    Publication Year: 1998, Page(s):1352 - 1357
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (191 KB)

    The construction of a surface model from range data may be undertaken at any point in a continuum of scales that reflects the level of detail of the resulting model. This continuum relates the construction parameters to the scale of the model. We propose methods to dynamically reprocess range data at different scales. The construction result from a single scale is automatically evaluated, causing ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 1998 Index IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 20

    Publication Year: 1998, Page(s):1395 - 1398
    Request permission for commercial reuse | PDF file iconPDF (2035 KB)
    Freely Available from IEEE
  • Subject index

    Publication Year: 1998, Page(s):1398 - 1408
    Request permission for commercial reuse | PDF file iconPDF (1459 KB)
    Freely Available from IEEE
  • Robust image corner detection through curvature scale space

    Publication Year: 1998, Page(s):1376 - 1381
    Cited by:  Papers (228)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3908 KB)

    This paper describes a novel method for image corner detection based on the curvature scale-space (CSS) representation. The first step is to extract edges from the original image using a Canny detector (1986). The corner points of an image are defined as points where image edges have their maxima of absolute curvature. The corner points are detected at a high scale of the CSS and tracked through m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the accuracy of Zernike moments for image analysis

    Publication Year: 1998, Page(s):1358 - 1364
    Cited by:  Papers (123)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (228 KB)

    We give a detailed analysis of the accuracy of Zernike moments in terms of their discretization errors and the reconstruction power. It is found that there is an inherent limitation in the precision of computing the Zernike moments due to the geometric nature of a circular domain. This is explained by relating the accuracy issue to a celebrated problem in analytic number theory of evaluating the l... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time American sign language recognition using desk and wearable computer based video

    Publication Year: 1998, Page(s):1371 - 1375
    Cited by:  Papers (409)  |  Patents (34)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (416 KB)

    We present two real-time hidden Markov model-based systems for recognizing sentence-level continuous American sign language (ASL) using a single camera to track the user's unadorned hands. The first system observes the user from a desk mounted camera and achieves 92 percent word accuracy. The second system mounts the camera in a cap worn by the user and achieves 98 percent accuracy (97 percent wit... View full abstract»

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

    Publication Year: 1998, Page(s):1308 - 1318
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (640 KB)

    A standard wavelet multiresolution analysis can be defined via a sequence of projectors onto a monotone sequence of closed vector subspaces possessing certain properties. We propose a nonlinear extension of this framework in which the vector subspaces are replaced by convex subsets. These sets are chosen so as to provide a recursive, monotone approximation scheme that allows for various signal and... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Bayesian framework for deformable pattern recognition with application to handwritten character recognition

    Publication Year: 1998, Page(s):1382 - 1388
    Cited by:  Papers (31)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (308 KB)

    Deformable models have recently been proposed for many pattern recognition applications due to their ability to handle large shape variations. These proposed approaches represent patterns or shapes as deformable models, which deform themselves to match with the input image, and subsequently feed the extracted information into a classifier. The three components-modeling, matching, and classificatio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling textured images using generalized long correlation models

    Publication Year: 1998, Page(s):1365 - 1370
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (336 KB)

    The long correlation (LC) models are a general class of random field (RF) models which are able to model correlations, extending over large image regions with few model parameters. The LC models have seen limited use, due to lack of an effective method for estimating the model parameters. In this work, we develop an estimation scheme for a very general form of this model and demonstrate its applic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A variable window approach to early vision

    Publication Year: 1998, Page(s):1283 - 1294
    Cited by:  Papers (82)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2476 KB)

    Early vision relies heavily on rectangular windows for tasks such as smoothing and computing correspondence. While rectangular windows are efficient, they yield poor results near object boundaries. We describe an efficient method for choosing an arbitrarily shaped connected window, in a manner that varies at each pixel. Our approach can be applied to several problems, including image restoration a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian function learning using MCMC methods

    Publication Year: 1998, Page(s):1319 - 1331
    Cited by:  Papers (32)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (612 KB)

    The paper deals with the problem of reconstructing a continuous 1D function from discrete noisy samples. The measurements may also be indirect in the sense that the samples may be the output of a linear operator applied to the function. Bayesian estimation provides a unified treatment of this class of problems. We show that a rigorous Bayesian solution can be efficiently implemented by resorting t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallelizing image feature extraction on coarse-grain machines

    Publication Year: 1998, Page(s):1389 - 1394
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (236 KB)

    In this paper, we present a fast parallel algorithm for feature extraction on coarse-grain MIMD machines. By maintaining algorithmic threads at each node, our algorithm enhances processor utilization and obtains large speed-ups. Our implementations show that, given a 1,024×1,024 image, speed-ups of 27.6 and 56.0 on a 32-node SP2 and a 64-node T3D can be achieved View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrating faces and fingerprints for personal identification

    Publication Year: 1998, Page(s):1295 - 1307
    Cited by:  Papers (195)  |  Patents (28)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2988 KB)

    An automatic personal identification system based solely on fingerprints or faces is often not able to meet the system performance requirements. We have developed a prototype biometrics system which integrates faces and fingerprints. The system overcomes the limitations of face recognition systems as well as fingerprint verification systems. The integrated prototype system operates in the identifi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive normalization of handwritten characters using global/local affine transformation

    Publication Year: 1998, Page(s):1332 - 1341
    Cited by:  Papers (35)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (440 KB)

    This paper introduces an adaptive or category-dependent normalization method that normalizes an input pattern against each reference pattern using global/local affine transformation (GAT/LAT) in a hierarchical manner as a general deformation model. Also, the normalization criterion is clearly defined as minimization of the mean of nearest-neighbor interpoint distances between each reference patter... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian classification with Gaussian processes

    Publication Year: 1998, Page(s):1342 - 1351
    Cited by:  Papers (191)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (352 KB)

    We consider the problem of assigning an input vector to one of m classes by predicting P(c|x) for c=1,...,m. For a two-class problem, the probability of class one given x is estimated by σ(y(x)), where σ(y)=1/(1+e-y). A Gaussian process prior is placed on y(x), and is combined with the training data to obtain predictions for new x points. We provide a Bayesian treatment, int... 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