IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 6 • Jun 1995

Filter Results

Displaying Results 1 - 10 of 10
  • Best-case results for nearest-neighbor learning

    Publication Year: 1995, Page(s):599 - 608
    Cited by:  Papers (14)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (968 KB)

    Proposes a theoretical model for analysis of classification methods, in which the teacher knows the classification algorithm and chooses examples in the best way possible. The authors apply this model using the nearest-neighbor learning algorithm, and develop upper and lower bounds on sample complexity for several different concept classes. For some concept classes, the sample complexity turns out... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Digitized circular arcs: characterization and parameter estimation

    Publication Year: 1995, Page(s):587 - 598
    Cited by:  Papers (24)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1024 KB)

    The digitization of a circular arc causes an inherent loss of geometrical information. Arcs with slightly different local curvature or position may lead to exactly the same digital pattern. In this paper the authors give a characterization of all centers and radii of circular arcs yielding the same digitization pattern. The radius of the arcs varies over the set. However, only one curvature or rad... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Subpixel edge location in binary images using dithering

    Publication Year: 1995, Page(s):629 - 634
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (500 KB)

    This paper concerns the problem of obtaining subpixel estimates of the locations of straight edges in binary digital images using dithering. By adding uniformly distributed independent random noise it is shown that estimation bias may be removed and that the estimation variance is inversely proportional to the length of the line segment. The sensitivity to incorrect dither amplitude is calculated,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modal matching for correspondence and recognition

    Publication Year: 1995, Page(s):545 - 561
    Cited by:  Papers (224)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1680 KB)

    Modal matching is a new method for establishing correspondences and computing canonical descriptions. The method is based on the idea of describing objects in terms of generalized symmetries, as defined by each object's eigenmodes. The resulting modal description is used for object recognition and categorization, where shape similarities are expressed as the amounts of modal deformation energy nee... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Moving-target search: a real-time search for changing goals

    Publication Year: 1995, Page(s):609 - 619
    Cited by:  Papers (43)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1192 KB)

    Considers the case of heuristic search where the goal may change during the course of the search. For example, the goal may be a target that actively avoids the problem solver. The authors present a moving-target search algorithm (MTS) to solve this problem. The authors prove that if the average speed of the target is slower than that of the problem solver, then the problem solver is guaranteed to... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Finding shortest paths on surfaces using level sets propagation

    Publication Year: 1995, Page(s):635 - 640
    Cited by:  Papers (102)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (464 KB)

    We present a new algorithm for determining minimal length paths between two regions on a three dimensional surface. The numerical implementation is based on finding equal geodesic distance contours from a given area. These contours are calculated as zero sets of a bivariate function designed to evolve so as to track the equal distance curves on the given surface. The algorithm produces all paths o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recursive estimation of motion, structure, and focal length

    Publication Year: 1995, Page(s):562 - 575
    Cited by:  Papers (262)  |  Patents (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1276 KB)

    Presents a formulation for recursive recovery of motion, pointwise structure, and focal length from feature correspondences tracked through an image sequence. In addition to adding focal length to the state vector, several representational improvements are made over earlier structure from motion formulations, yielding a stable and accurate estimation framework which applies uniformly to both true ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image relaxation: restoration and feature extraction

    Publication Year: 1995, Page(s):620 - 624
    Cited by:  Papers (15)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (484 KB)

    The techniques of a posteriori image restoration and iterative image feature extraction are described and compared. Image feature extraction methods known as graduated nonconvexity (GNC); variable conductance diffusion (VCD), anisotropic diffusion, and biased anisotropic diffusion (BAD), which extract edges from noisy images, are compared with a restoration/feature extraction method known as mean ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On discontinuity-adaptive smoothness priors in computer vision

    Publication Year: 1995, Page(s):576 - 586
    Cited by:  Papers (90)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (956 KB)

    A variety of analytic and probabilistic models in connection with Markov random fields (MRFs) have been proposed in the last decade for solving low level vision problems involving discontinuities. This paper presents a systematic study of these models and defines a general discontinuity adaptive (DA) MRF model. By analyzing the Euler equation associated with the energy minimization, it shows that ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discontinuity-preserving and viewpoint invariant reconstruction of visible surfaces using a first order regularization

    Publication Year: 1995, Page(s):624 - 629
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (564 KB)

    This paper describes the application of a first order regularization technique to the reconstruction of visible surfaces. Our approach is a computationally efficient first order method that simultaneously achieves approximate invariance and preservation of discontinuities. It is also robust with respect to the smoothing parameter λ. The robustness property to λ allows a free choice o... 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
Sven Dickinson
University of Toronto
e-mail: sven@cs.toronto.edu