By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 1 • Date Jan 1992

Filter Results

Displaying Results 1 - 6 of 6
  • A highly robust estimator through partially likelihood function modeling and its application in computer vision

    Publication Year: 1992, Page(s):19 - 35
    Cited by:  Papers (26)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1292 KB)

    The authors present a highly robust estimator, known as the model fitting (MF) estimator for general regression. They explain that high robustness becomes possible through partially but completely modeling the unknown log likelihood function. The partial modeling takes place by taking the Bayesian statistical decision rule and a number of important heuristics into consideration while maximizing th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the problem of local minima in backpropagation

    Publication Year: 1992, Page(s):76 - 86
    Cited by:  Papers (127)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (932 KB)

    The authors propose a theoretical framework for backpropagation (BP) in order to identify some of its limitations as a general learning procedure and the reasons for its success in several experiments on pattern recognition. The first important conclusion is that examples can be found in which BP gets stuck in local minima. A simple example in which BP can get stuck during gradient descent without... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A cost minimization approach to edge detection using simulated annealing

    Publication Year: 1992, Page(s):3 - 18
    Cited by:  Papers (53)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1544 KB)

    The authors cast edge detection as a problem in cost minimization. This is achieved by the formulation of a cost function that evaluates the quality of edge configurations. The function is a linear sum of weighted cost factors. The cost factors capture desirable characteristics of edges such as accuracy in localization, thinness, and continuity. Edges are detected by finding the edge configuration... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A two-stage algorithm for discontinuity-preserving surface reconstruction

    Publication Year: 1992, Page(s):36 - 55
    Cited by:  Papers (72)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2672 KB)

    A two-stage algorithm for visual surface reconstruction from scattered data while preserving discontinuities is presented. The first stage consists of a robust local approximation algorithm (the moving least median of squares (MLMS) of error) to clean the data and create a grid from the original scattered data points. This process is discontinuity preserving. The second stage introduces a weighted... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On reliable computation with formal neurons

    Publication Year: 1992, Page(s):87 - 91
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    The authors investigate the computing capabilities of formal McCulloch-Pitts neurons when errors are permitted in decisions. They assume that m decisions are to be made on a randomly specified m set of points in n space and that an error tolerance of εm decision errors is allowed, with 0⩽ε<1/2. The authors are interested in how large an ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulating the grassfire transform using an active contour model

    Publication Year: 1992, Page(s):56 - 75
    Cited by:  Papers (125)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2004 KB)

    A method for shape description of planar objects that integrates both region and boundary features is presented. The method is an implementation of a 2D dynamic grassfire that relies on a distance surface on which elastic contours minimize an energy function. The method is based on an active contour model. Numerous implementation aspects of the shape description method were optimized. A Euclidean ... 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