Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.

26-26 Aug. 2004

Go

Filter Results

Displaying Results 1 - 25 of 259
  • Proceedings of the 17th International Conference on Pattern Recognition

    Publication Year: 2004, Page(s): i
    Request permission for commercial reuse | PDF file iconPDF (196 KB)
    Freely Available from IEEE
  • Proceedings of the 17 th International Conference on Pattern Recognition

    Publication Year: 2004, Page(s): iii
    Request permission for commercial reuse | PDF file iconPDF (192 KB)
    Freely Available from IEEE
  • Copyright page

    Publication Year: 2004, Page(s): iv
    Request permission for commercial reuse | PDF file iconPDF (191 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2004, Page(s):v - xx
    Request permission for commercial reuse | PDF file iconPDF (249 KB)
    Freely Available from IEEE
  • Message from the Chairs

    Publication Year: 2004, Page(s): xxi
    Request permission for commercial reuse | PDF file iconPDF (173 KB) | HTML iconHTML
    Freely Available from IEEE
  • Organizing Committee

    Publication Year: 2004, Page(s): xxii
    Request permission for commercial reuse | PDF file iconPDF (175 KB)
    Freely Available from IEEE
  • Track one: computer vision with associated theme: machine vision applications

    Publication Year: 2004, Page(s): xxiii
    Request permission for commercial reuse | PDF file iconPDF (178 KB) | HTML iconHTML
    Freely Available from IEEE
  • Track two: pattern recognition and neural networks with associated theme:document analysis

    Publication Year: 2004, Page(s): xxiv
    Cited by:  Patents (1)
    Request permission for commercial reuse | PDF file iconPDF (177 KB) | HTML iconHTML
    Freely Available from IEEE
  • Track three: image and signal processing

    Publication Year: 2004, Page(s): xxv
    Request permission for commercial reuse | PDF file iconPDF (179 KB) | HTML iconHTML
    Freely Available from IEEE
  • Track four: multimedia systems

    Publication Year: 2004, Page(s): xxvi
    Request permission for commercial reuse | PDF file iconPDF (175 KB) | HTML iconHTML
    Freely Available from IEEE
  • Track five: architecture, technology and tools

    Publication Year: 2004, Page(s): xxvii
    Request permission for commercial reuse | PDF file iconPDF (172 KB) | HTML iconHTML
    Freely Available from IEEE
  • Additional reviewers

    Publication Year: 2004, Page(s):xxviii - xxxi
    Request permission for commercial reuse | PDF file iconPDF (185 KB)
    Freely Available from IEEE
  • Message from the president of the IAPR

    Publication Year: 2004, Page(s): xxxii
    Request permission for commercial reuse | PDF file iconPDF (174 KB) | HTML iconHTML
    Freely Available from IEEE
  • Members of the Governing Board of IAPR

    Publication Year: 2004, Page(s): xxxiii
    Request permission for commercial reuse | PDF file iconPDF (175 KB) | HTML iconHTML
    Freely Available from IEEE
  • IAPR Committees

    Publication Year: 2004, Page(s):xxxiv - xxxv
    Request permission for commercial reuse | PDF file iconPDF (174 KB)
    Freely Available from IEEE
  • IAPR technical Committees

    Publication Year: 2004, Page(s): xxxvi
    Request permission for commercial reuse | PDF file iconPDF (178 KB)
    Freely Available from IEEE
  • IAPR member societies

    Publication Year: 2004, Page(s):xxxvii - xxxix
    Request permission for commercial reuse | PDF file iconPDF (193 KB)
    Freely Available from IEEE
  • Representing cultural heritage in digital forms for VR systems through computer vision techniques

    Publication Year: 2004, Page(s):1 - 6 Vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (606 KB) | HTML iconHTML

    This work overviews our research on digital preservation of cultural assets and digital restoration of their original appearance. Geometric models are digitally achieved through a pipeline consisting of scanning, registering and merging multiple range images. We have developed a robust simultaneous registration method and an efficient and robust voxel-based integration method. On the geometric mod... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visual pattern recognition in the years ahead

    Publication Year: 2004, Page(s):7 - 10 Vol.4
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (251 KB) | HTML iconHTML

    Conventional classification algorithms have already reached a plateau at the trade-off imposed by the bias due to the structure of the classifier and the variance due to the limited size of the training set. The latter may be alleviated by exploiting known constraints, including class and style priors, language models, statistical correlations between spatially proximate patterns, statistical depe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A symmetric convexity measure

    Publication Year: 2004, Page(s):11 - 14 Vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (334 KB) | HTML iconHTML

    A new area-based convexity measure for polygons is described. It has the desirable properties that it is not sensitive to small boundary defects, and it is symmetric with respect to intrusions and protrusions. The measure requires a maximally overlapping convex polygon, and this is efficiently estimated using a genetic algorithm. Examples of the measures application to medical image analysis are s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shape metamorphism using p-Laplacian equation

    Publication Year: 2004, Page(s):15 - 18 Vol.4
    Cited by:  Papers (4)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1153 KB) | HTML iconHTML

    We present a new approach for shape metamorphism, which is a process of gradually changing a source shape (known) through intermediate shapes (unknown) into a target shape (known). The problem, when represented with implicit scalar function, is under-constrained, and regularization is needed. Using the p-Laplacian equation (PLE), we generalize a series of regularization terms based on the gradient... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimal inference for hierarchical skeleton abstraction

    Publication Year: 2004, Page(s):19 - 22 Vol.4
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (426 KB) | HTML iconHTML

    Skeletons are well-known representations that accommodate shape abstraction and qualitative shape matching. However, skeletons are sometimes unstable to compute and sensitive to shape detail, thus making shape abstraction and matching difficult. To address these problems, we propose a principled framework that generates a simplified, abstracted skeleton hierarchy by analyzing the quasi-stable poin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parameterisation invariant statistical shape models

    Publication Year: 2004, Page(s):23 - 26 Vol.4
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (328 KB) | HTML iconHTML

    In this paper novel theory to automate shape modelling is described. The main idea is to develop a theory that is intrinsically defined for curves, as opposed to a finite sample of points along the curves. The major problem here is to define shape variation in a way that is invariant to curve parametrisations. Instead of representing continuous curves using landmarks, the problem is treated analyt... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Morse homology descriptor for shape characterization

    Publication Year: 2004, Page(s):27 - 30 Vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (311 KB) | HTML iconHTML

    We propose a new topological method for shape description that is suitable for any multi-dimensional data set that can be modelled as a manifold. The description is obtained for all pairs (M, f), where M is a closed smooth manifold and f a Morse function defined on M. More precisely, we characterize the topology of all pairs of lower level sets (M/sub y/, M/sub x/) of f, where M/sub a/ = f/sup -1/... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Conformal method for quantitative shape extraction: Performance evaluation

    Publication Year: 2004, Page(s):31 - 35 Vol.4
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (407 KB) | HTML iconHTML

    We evaluate our developed conformal method for quantitative shape extraction from unorganized 3D oriented point clouds. The conformal method has been tested previously on real, noisy, 3D data. Here we focus on the empirical evaluation of its performance on synthetic, ground truth data, and comparisons with other methods for quantitative extraction of mean and Gauss curvatures presented in the lite... View full abstract»

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