By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 2 • Date Feb. 2005

Filter Results

Displaying Results 1 - 21 of 21
  • [Front cover]

    Publication Year: 2005, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (127 KB)
    Freely Available from IEEE
  • [Inside front cover]

    Publication Year: 2005, Page(s): c2
    Request permission for commercial reuse | PDF file iconPDF (75 KB)
    Freely Available from IEEE
  • Introduction of New Associate Editors

    Publication Year: 2005, Page(s): 161
    Request permission for commercial reuse | PDF file iconPDF (57 KB)
    Freely Available from IEEE
  • The humanID gait challenge problem: data sets, performance, and analysis

    Publication Year: 2005, Page(s):162 - 177
    Cited by:  Papers (442)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2631 KB) | HTML iconHTML

    Identification of people by analysis of gait patterns extracted from video has recently become a popular research problem. However, the conditions under which the problem is "solvable" are not understood or characterized. To provide a means for measuring progress and characterizing the properties of gait recognition, we introduce the humanlD gait challenge problem. The challenge problem consists o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Separating reflection components of textured surfaces using a single image

    Publication Year: 2005, Page(s):178 - 193
    Cited by:  Papers (107)  |  Patents (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3713 KB) | HTML iconHTML

    In inhomogeneous objects, highlights are linear combinations of diffuse and specular reflection components. To our knowledge, all methods that use a single input image require explicit color segmentation to deal with multicolored surfaces. Unfortunately, for complex textured images, current color segmentation algorithms are still problematic to segment correctly. Consequently, a method without exp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using geometric constraints through parallelepipeds for calibration and 3D modeling

    Publication Year: 2005, Page(s):194 - 207
    Cited by:  Papers (33)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (900 KB) | HTML iconHTML

    This paper concerns the incorporation of geometric information in camera calibration and 3D modeling. Using geometric constraints enables more stable results and allows us to perform tasks with fewer images. Our approach is motivated and developed within a framework of semi-automatic 3D modeling, where the user defines geometric primitives and constraints between them. In this paper, first a duali... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Representation and detection of deformable shapes

    Publication Year: 2005, Page(s):208 - 220
    Cited by:  Papers (59)  |  Patents (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1092 KB) | HTML iconHTML

    We describe some techniques that can be used to represent and detect deformable shapes in images. The main difficulty with deformable template models is the very large or infinite number of possible nonrigid transformations of the templates. This makes the problem of finding an optimal match of a deformable template to an image incredibly hard. Using a new representation for deformable shapes, we ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • First order error propagation of the Procrustes method for 3D attitude estimation

    Publication Year: 2005, Page(s):221 - 229
    Cited by:  Papers (21)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (493 KB) | HTML iconHTML

    The well-known Procrustes method determines the optimal rigid body motion that registers two point clouds by minimizing the square distances of the residuals. In this paper, we perform the first order error analysis of this method for the 3D case, fully specifying how directional noise in the point clouds affects the estimated parameters of the rigid body motion. These results are much more specif... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • KPCA plus LDA: a complete kernel Fisher discriminant framework for feature extraction and recognition

    Publication Year: 2005, Page(s):230 - 244
    Cited by:  Papers (374)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1091 KB) | HTML iconHTML

    This paper examines the theory of kernel Fisher discriminant analysis (KFD) in a Hilbert space and develops a two-phase KFD framework, i.e., kernel principal component analysis (KPCA) plus Fisher linear discriminant analysis (LDA). This framework provides novel insights into the nature of KFD. Based on this framework, the authors propose a complete kernel Fisher discriminant analysis (CKFD) algori... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • How to complete performance graphs in content-based image retrieval: add generality and normalize scope

    Publication Year: 2005, Page(s):245 - 251
    Cited by:  Papers (28)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (403 KB) | HTML iconHTML

    The performance of a content-based image retrieval (CBIR) system, presented in the form of precision-recall or precision-scope graphs, offers an incomplete overview of the system under study: the influence of the irrelevant items (embedding) is obscured. We propose a comprehensive and well-normalized description of the ranking performance compared to the performance of an ideal retrieval system de... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visually distinct patterns with matching subband statistics

    Publication Year: 2005, Page(s):252 - 264
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1153 KB) | HTML iconHTML

    A commonly used representation of a visual pattern is a statistical distribution measured from the output of a bank of filters (Gaussian, Laplacian, Gabor, etc.). Both marginal and joint distributions of filter responses have been advocated and effectively used for a variety of vision tasks, including texture classification, texture synthesis, object detection, and image retrieval. This paper exam... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using points at infinity for parameter decoupling in camera calibration

    Publication Year: 2005, Page(s):265 - 270
    Cited by:  Papers (11)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (472 KB) | HTML iconHTML

    The majority of camera calibration methods, including the gold standard algorithm, use point-based information and simultaneously estimate all calibration parameters. In contrast, we propose a novel calibration method that exploits line orientation information and decouples the problem into two simpler stages. We formulate the problem as minimization of the lateral displacement between single proj... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Outward-looking circular motion analysis of large image sequences

    Publication Year: 2005, Page(s):271 - 277
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (991 KB) | HTML iconHTML

    This work presents a novel and simple method of analyzing the motion of a large image sequence captured by a calibrated outward-looking video camera moving on a circular trajectory for large-scale environment applications. Previous circular motion algorithms mainly focus on inward-looking turntable-like setups. They are not suitable for outward-looking motion where the conic trajectory of correspo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Symbol recognition via statistical integration of pixel-level constraint histograms: a new descriptor

    Publication Year: 2005, Page(s):278 - 281
    Cited by:  Papers (38)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (299 KB) | HTML iconHTML

    A new descriptor for symbol recognition is proposed. 1) A histogram is constructed for every pixel to figure out the distribution of the constraints among the other pixels. 2) All the histograms are statistically integrated to form a feature vector with fixed dimension. The robustness and invariance were experimentally confirmed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improving performance of distribution tracking through background mismatch

    Publication Year: 2005, Page(s):282 - 287
    Cited by:  Papers (23)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (717 KB) | HTML iconHTML

    This paper proposes a new density matching method based on background mismatching for tracking of nonrigid moving objects. The new tracking method extends the idea behind the original density-matching tracker, which tracks an object by finding a contour in which the photometric density sampled from the enclosed region most closely matches a model density. This method can be quite sensitive to the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Fourier theory for cast shadows

    Publication Year: 2005, Page(s):288 - 295
    Cited by:  Papers (22)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1455 KB) | HTML iconHTML

    Cast shadows can be significant in many computer vision applications, such as lighting-insensitive recognition and surface reconstruction. Nevertheless, most algorithms neglect them, primarily because they involve nonlocal interactions in nonconvex regions, making formal analysis difficult. However, many real instances map closely to canonical configurations like a wall, a V-groove type structure,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spacetime stereo: a unifying framework for depth from triangulation

    Publication Year: 2005, Page(s):296 - 302
    Cited by:  Papers (130)  |  Patents (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1520 KB) | HTML iconHTML

    Depth from triangulation has traditionally been investigated in a number of independent threads of research, with methods such as stereo, laser scanning, and coded structured light considered separately. We propose a common framework called spacetime stereo that unifies and generalizes many of these previous methods. To show the practical utility of the framework, we develop two new algorithms for... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Additions to 2004 Annual Index

    Publication Year: 2005, Page(s): 303
    Request permission for commercial reuse | PDF file iconPDF (78 KB)
    Freely Available from IEEE
  • [Advertisement]

    Publication Year: 2005, Page(s): 304
    Request permission for commercial reuse | PDF file iconPDF (402 KB)
    Freely Available from IEEE
  • TPAMI Information for authors

    Publication Year: 2005, Page(s): c3
    Request permission for commercial reuse | PDF file iconPDF (75 KB)
    Freely Available from IEEE
  • [Back cover]

    Publication Year: 2005, Page(s): c4
    Request permission for commercial reuse | PDF file iconPDF (127 KB)
    Freely Available from IEEE

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