By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 11 • Date Nov 1997

Filter Results

Displaying Results 1 - 13 of 13
  • Estimation and compensation of subpixel edge localization error

    Publication Year: 1997, Page(s):1278 - 1284
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (488 KB)

    We propose and analyze a method for improving the performance of subpixel edge localization (EL) techniques through compensation of the systematic portion of the localization error. The method is based on the estimation of the EL characteristic through statistical analysis of a test image and is independent of the EL technique in use View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Inference of surfaces, 3D curves, and junctions from sparse, noisy, 3D data

    Publication Year: 1997, Page(s):1265 - 1277
    Cited by:  Papers (88)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (720 KB)

    We address the problem of obtaining dense surface information from a sparse set of 3D data in the presence of spurious noise samples. The input can be in the form of points, or points with an associated tangent or normal, allowing both position and direction to be corrupted by noise. Most approaches treat the problem as an interpolation problem, which is solved by fitting a surface such as a membr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An integrated model for evaluating the amount of data required for reliable recognition

    Publication Year: 1997, Page(s):1251 - 1264
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (268 KB)

    Many recognition procedures rely on the consistency of a subset of data features with a hypothesis as the sufficient evidence to the presence of the corresponding object. We analyze here the performance of such procedures, using a probabilistic model, and provide expressions for the sufficient size of such data subsets, that, if consistent, guarantee the validity of the hypotheses with arbitrary c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Prior learning and Gibbs reaction-diffusion

    Publication Year: 1997, Page(s):1236 - 1250
    Cited by:  Papers (134)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2828 KB)

    This article addresses two important themes in early visual computation: it presents a novel theory for learning the universal statistics of natural images, and, it proposes a general framework of designing reaction-diffusion equations for image processing. We studied the statistics of natural images including the scale invariant properties, then generic prior models were learned to duplicate the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D part segmentation using simulated electrical charge distributions

    Publication Year: 1997, Page(s):1223 - 1235
    Cited by:  Papers (55)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (880 KB)

    A novel approach to 3D part segmentation is presented. It is a well-known physical fact that electrical charge on the surface of a conductor tends to accumulate at a sharp convexity and vanish at a sharp concavity. Thus, object part boundaries, which are usually denoted by a sharp surface concavity, can be detected by simulating the electrical charge density over the object surface and locating su... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Geometric separation of partially overlapping nonrigid objects applied to automatic chromosome classification

    Publication Year: 1997, Page(s):1212 - 1222
    Cited by:  Papers (64)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (312 KB)

    A common task in cytogenetic tests is the classification of human chromosomes. Successful separation between touching and overlapping chromosomes in a metaphase image is vital for correct classification. Current systems for automatic chromosome classification are mostly interactive and require human intervention for correct separation between touching and overlapping chromosomes. Since chromosomes... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A discrete expression of Canny's criteria for step edge detector performances evaluation

    Publication Year: 1997, Page(s):1199 - 1211
    Cited by:  Papers (48)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (520 KB)

    Optimal filters for edge detection are usually developed in the continuous domain and then transposed by sampling to the discrete domain. Simpler filters are directly defined in the discrete domain. We define criteria to compare filter performances in the discrete domain. Canny has defined (1983, 1986) three criteria to derive the equation of an optimal filter for step edge detection: good detecti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance assessment through bootstrap

    Publication Year: 1997, Page(s):1185 - 1198
    Cited by:  Papers (39)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1296 KB)

    A new performance evaluation paradigm for computer vision systems is proposed. In real situation, the complexity of the input data and/or of the computational procedure can make traditional error propagation methods infeasible. The new approach exploits a resampling technique recently introduced in statistics, the bootstrap. Distributions for the output variables are obtained by perturbing the nui... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A framework for performance characterization of intermediate-level grouping modules

    Publication Year: 1997, Page(s):1306 - 1312
    Cited by:  Papers (30)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1160 KB)

    We present five performance measures to evaluate grouping modules in the context of constrained search and indexing based object recognition. Using these measures, we demonstrate a sound experimental framework, based on statistical ANOVA tests, to compare and contrast three edge based organization modules, namely, those of Etemadi et al. (1991), Jacobs (1996), and Sarkar-Boyer (1993) in the domain... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scene understanding by rule evaluation

    Publication Year: 1997, Page(s):1284 - 1288
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (792 KB)

    We consider how machine learning can be used to help solve the problem of identifying objects or structures composed of parts in complex scenes. We first discuss a conditional rule generation technique that is designed to describe structures using part attributes and their relations. We then show how the resultant rules can be used for region labeling and examine constraint propagation techniques ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Superquadrics for segmenting and modeling range data

    Publication Year: 1997, Page(s):1289 - 1295
    Cited by:  Papers (69)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (604 KB)

    We present an approach to reliable and efficient recovery of part-descriptions in terms of superquadric models from range data. We show that superquadrics can directly be recovered from unsegmented data, thus avoiding any presegmentation steps (e.g. in terms of surfaces). The approach is based on the recover-and-select paradigm. We present several experiments on real and synthetic range images, wh... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computational Bayesian analysis of hidden Markov mesh models

    Publication Year: 1997, Page(s):1296 - 1300
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (144 KB)

    Versions of the Gibbs sampler are derived for the analysis of data from the hidden Markov mesh random fields sometimes used in image analysis. This provides a numerical approach to the otherwise intractable Bayesian analysis of these problems. Detailed formulation is provided for particular examples based on Devijver's Markov mesh model (1988), and the BUGS package is used to do the computations. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Joint induction of shape features and tree classifiers

    Publication Year: 1997, Page(s):1300 - 1305
    Cited by:  Papers (57)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (736 KB)

    We introduce a very large family of binary features for two-dimensional shapes. The salient ones for separating particular shapes are determined by inductive learning during the construction of classification trees. There is a feature for every possible geometric arrangement of local topographic codes. The arrangements express coarse constraints on relative angles and distances among the code loca... 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