By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 6 • Date June 2003

Filter Results

Displaying Results 1 - 12 of 12
  • Guest editors' introduction to the special section on perceptual organization in computer vision

    Publication Year: 2003, Page(s): 641
    Request permission for commercial reuse | PDF file iconPDF (297 KB) | HTML iconHTML
    Freely Available from IEEE
  • Statistical modeling and conceptualization of visual patterns

    Publication Year: 2003, Page(s):691 - 712
    Cited by:  Papers (35)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4330 KB) | HTML iconHTML

    Natural images contain an overwhelming number of visual patterns generated by diverse stochastic processes. Defining and modeling these patterns is of fundamental importance for generic vision tasks, such as perceptual organization, segmentation, and recognition. The objective of this epistemological paper is to summarize various threads of research in the literature and to pursue a unified framew... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An in-depth study of graph partitioning measures for perceptual organization

    Publication Year: 2003, Page(s):642 - 660
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2943 KB) | HTML iconHTML

    In recent years, one of the effective engines for perceptual organization of low-level image features is based on the partitioning of a graph representation that captures Gestalt inspired local structures, such as similarity, proximity, continuity, parallelism, and perpendicularity, over the low-level image features. Mainly motivated by computational efficiency considerations, this graph partition... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A topology preserving level set method for geometric deformable models

    Publication Year: 2003, Page(s):755 - 768
    Cited by:  Papers (169)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1928 KB) | HTML iconHTML

    Active contour and surface models, also known as deformable models, are powerful image segmentation techniques. Geometric deformable models implemented using level set methods have advantages over parametric models due to their intrinsic behavior, parameterization independence, and ease of implementation. However, a long claimed advantage of geometric deformable models-the ability to automatically... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Bayesian discriminating features method for face detection

    Publication Year: 2003, Page(s):725 - 740
    Cited by:  Papers (87)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (8826 KB) | HTML iconHTML

    This paper presents a novel Bayesian discriminating features (BDF) method for multiple frontal face detection. The BDF method, which is trained on images from only one database, yet works on test images from diverse sources, displays robust generalization performance. The novelty of this paper comes from the integration of the discriminating feature analysis of the input image, the statistical mod... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Contrast restoration of weather degraded images

    Publication Year: 2003, Page(s):713 - 724
    Cited by:  Papers (209)  |  Patents (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3060 KB) | HTML iconHTML

    Images of outdoor scenes captured in bad weather suffer from poor contrast. Under bad weather conditions, the light reaching a camera is severely scattered by the atmosphere. The resulting decay in contrast varies across the scene and is exponential in the depths of scene points. Therefore, traditional space invariant image processing techniques are not sufficient to remove weather effects from im... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Contour grouping with prior models

    Publication Year: 2003, Page(s):661 - 674
    Cited by:  Papers (28)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3330 KB) | HTML iconHTML

    Conventional approaches to perceptual grouping assume little specific knowledge about the object(s) of interest. However, there are many applications in which such knowledge is available and useful. Here, we address the problem of finding the bounding contour of an object in an image when some prior knowledge about the object is available. We introduce a framework for combining prior probabilistic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image segmentation with ratio cut

    Publication Year: 2003, Page(s):675 - 690
    Cited by:  Papers (93)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (6363 KB) | HTML iconHTML

    This paper proposes a new cost function, cut ratio, for segmenting images using graph-based methods. The cut ratio is defined as the ratio of the corresponding sums of two different weights of edges along the cut boundary and models the mean affinity between the segments separated by the boundary per unit boundary length. This new cost function allows the image perimeter to be segmented, guarantee... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Expandable Bayesian networks for 3D object description from multiple views and multiple mode inputs

    Publication Year: 2003, Page(s):769 - 774
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1805 KB) | HTML iconHTML

    Computing 3D object descriptions from images is an important goal of computer vision. A key problem here is the evaluation of a hypothesis based on evidence that is uncertain. There have been few efforts on applying formal reasoning methods to this problem. In multiview and multimode object description problems, reasoning is required on evidence features extracted from multiple images and noninten... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mosaicing new views: the Crossed-Slits projection

    Publication Year: 2003, Page(s):741 - 754
    Cited by:  Papers (65)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4695 KB) | HTML iconHTML

    We introduce anew kind of mosaicing, where the position of the sampling strip varies as a function of the input camera location. The new images that are generated this way correspond to a new projection model defined by two slits, termed here the Crossed-Slits (X-Slits) projection. In this projection model, every 3D point is projected by a ray defined as the line that passes through that point and... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature selection for multiclass discrimination via mixed-integer linear programming

    Publication Year: 2003, Page(s):779 - 783
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (444 KB) | HTML iconHTML

    We reformulate branch-and-bound feature selection employing L or particular Lp metrics, as mixed-integer linear programming (MILP) problems, affording convenience of widely available MILP solvers. These formulations offer direct influence over individual pairwise interclass margins, which is useful for feature selection in multiclass settings. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The generic viewpoint assumption and planar bias

    Publication Year: 2003, Page(s):775 - 778
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (257 KB) | HTML iconHTML

    We show that generic viewpoint and lighting assumptions resolve standard visual ambiguities by biasing toward planar surfaces. Our model uses orthographic projection with a two-dimensional affine warp and Lambertian reflectance functions, including cast and attached shadows. We use uniform priors on nuisance variables such as viewpoint direction and the light source. Limitations of using uniform p... 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