By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 2 • Date Feb 2004

Filter Results

Displaying Results 1 - 20 of 20
  • Disclaimer: "Relative fuzzy connectedness and object definition: theory, algorithms, and applications in image segmentation"

    Publication Year: 2004, Page(s): 287
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (180 KB) | HTML iconHTML

    First Page of the Article
    View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Guest editors' introduction to the special section on energy minimization methods in computer vision and pattern recognition

    Publication Year: 2004, Page(s):145 - 146
    Request permission for commercial reuse | PDF file iconPDF (256 KB) | HTML iconHTML
    Freely Available from IEEE
  • What energy functions can be minimized via graph cuts?

    Publication Year: 2004, Page(s):147 - 159
    Cited by:  Papers (1213)  |  Patents (24)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (597 KB) | HTML iconHTML

    In the last few years, several new algorithms based on graph cuts have been developed to solve energy minimization problems in computer vision. Each of these techniques constructs a graph such that the minimum cut on the graph also minimizes the energy. Yet, because these graph constructions are complex and highly specific to a particular energy function, graph cuts have seen limited application t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised learning of an Atlas from unlabeled point-sets

    Publication Year: 2004, Page(s):160 - 172
    Cited by:  Papers (42)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5736 KB) | HTML iconHTML

    One of the key challenges in deformable shape modeling is the problem of estimating a meaningful average or mean shape from a set of unlabeled shapes. We present a new joint clustering and matching algorithm that is capable of computing such a mean shape from multiple shape samples which are represented by unlabeled point-sets. An iterative bootstrap process is used wherein multiple shape sample p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation given partial grouping constraints

    Publication Year: 2004, Page(s):173 - 183
    Cited by:  Papers (89)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1489 KB) | HTML iconHTML

    We consider data clustering problems where partial grouping is known a priori. We formulate such biased grouping problems as a constrained optimization problem, where structural properties of the data define the goodness of a grouping and partial grouping cues define the feasibility of a grouping. We enforce grouping smoothness and fairness on labeled data points so that sparse partial grouping in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nonparametric multiscale energy-based mode and its application in some imagery problems

    Publication Year: 2004, Page(s):184 - 197
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3583 KB) | HTML iconHTML

    This paper investigates the use of a nonparametric regularization energy term for devising a example-based rendering and segmentation technique. We have stated this problem in the multiresolution energy minimization framework and exploited the multiscale structure proposed by Wei and Levoy for the texture synthesis problem. In this nonparametric energy minimization framework, we also propose a com... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 'Online recognition of Chinese characters: the state-of-the-art

    Publication Year: 2004, Page(s):198 - 213
    Cited by:  Papers (131)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1193 KB) | HTML iconHTML

    Online handwriting recognition is gaining renewed interest owing to the increase of pen computing applications and new pen input devices. The recognition of Chinese characters is different from western handwriting recognition and poses a special challenge. To provide an overview of the technical status and inspire future research, this paper reviews the advances in online Chinese character recogni... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spectral grouping using the Nystrom method

    Publication Year: 2004, Page(s):214 - 225
    Cited by:  Papers (375)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2617 KB) | HTML iconHTML

    Spectral graph theoretic methods have recently shown great promise for the problem of image segmentation. However, due to the computational demands of these approaches, applications to large problems such as spatiotemporal data and high resolution imagery have been slow to appear. The contribution of this paper is a method that substantially reduces the computational requirements of grouping algor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generalized parallel-perspective stereo mosaics from airborne video

    Publication Year: 2004, Page(s):226 - 237
    Cited by:  Papers (24)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2843 KB) | HTML iconHTML

    In this paper, we present a new method for automatically and efficiently generating stereoscopic mosaics by seamless registration of images collected by a video camera mounted on an airborne platform. Using a parallel-perspective representation, a pair of geometrically registered stereo mosaics can be precisely constructed under quite general motion. A novel parallel ray interpolation for stereo m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A formal classification of 3D medial axis points and their local geometry

    Publication Year: 2004, Page(s):238 - 251
    Cited by:  Papers (22)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3302 KB) | HTML iconHTML

    This paper proposes a novel hypergraph skeletal representation for 3D shape based on a formal derivation of the generic structure of its medial axis. By classifying each skeletal point by its order of contact, we show that, genetically, the medial axis consists of five types of points, which are then organized into sheets, curves, and points: 1) sheets (manifolds with boundary) which are the locus... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative evaluation of length estimators of digital curves

    Publication Year: 2004, Page(s):252 - 258
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2121 KB) | HTML iconHTML

    This paper compares previously published length estimators in image analysis having digitized curves as input. The evaluation uses multigrid convergence (theoretical results and measured speed of convergence) and further measures as criteria. This paper also suggests a new gradient-based method for length estimation, and combines a previously proposed length estimator for straight segments with a ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Repetitive motion analysis: segmentation and event classification

    Publication Year: 2004, Page(s):258 - 263
    Cited by:  Papers (38)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2237 KB) | HTML iconHTML

    Acquisition, analysis, and classification of repetitive human motion for the assessment of postural stress is of central importance to ergonomics practitioners. We present a two-threshold, multidimensional segmentation algorithm to automatically decompose a complex motion into a sequence of simple linear dynamic models. No a priori assumptions were made about the number of models that comprise the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • From FNS to HEIV: a link between two vision parameter estimation methods

    Publication Year: 2004, Page(s):264 - 268
    Cited by:  Papers (24)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (903 KB) | HTML iconHTML

    Problems requiring accurate determination of parameters from image-based quantities arise often in computer vision. Two recent, independently developed frameworks for estimating such parameters are the FNS and HEIV schemes. Here, it is shown that FNS and a core version of HEIV are essentially equivalent, solving a common underlying equation via different means. The analysis is driven by the search... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptation in statistical pattern recognition using tangent vectors

    Publication Year: 2004, Page(s):269 - 274
    Cited by:  Papers (24)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1565 KB) | HTML iconHTML

    We integrate the tangent method into a statistical framework for classification analytically and practically. The resulting consistent framework for adaptation allows us to efficiently estimate the tangent vectors representing the variability. The framework improves classification results on two real-world pattern recognition tasks from the domains handwritten character recognition and automatic s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Error analysis of pure rotation-based self-calibration

    Publication Year: 2004, Page(s):275 - 280
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (933 KB) | HTML iconHTML

    Self-calibration using pure rotation is a well-known technique and has been shown to be a reliable means for recovering intrinsic camera parameters. However, in practice, it is virtually impossible to ensure that the camera motion for this type of self-calibration is a pure rotation. In this paper, we present an error analysis of recovered intrinsic camera parameters due to the presence of transla... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Investigating hidden Markov models' capabilities in 2D shape classification

    Publication Year: 2004, Page(s):281 - 286
    Cited by:  Papers (45)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (525 KB) | HTML iconHTML

    In this paper, Hidden Markov Models (HMMs) are investigated for the purpose of classifying planar shapes represented by their curvature coefficients. In the training phase, special attention is devoted to the initialization and model selection issues, which make the learning phase particularly effective. The results of tests on different data sets show that the proposed system is able to accuratel... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IEEE Transactions on Pattern Analysis and Machine Intelligence - Table of Contents

    Publication Year: 2004, Page(s):01 - 04
    Request permission for commercial reuse | PDF file iconPDF (303 KB)
    Freely Available from IEEE
  • IEEE Transactions on Pattern Analysis and Machine Intelligence

    Publication Year: 2004, Page(s): 0_2
    Request permission for commercial reuse | PDF file iconPDF (224 KB)
    Freely Available from IEEE
  • TPAMI: Information for authors

    Publication Year: 2004, Page(s): 03
    Request permission for commercial reuse | PDF file iconPDF (224 KB)
    Freely Available from IEEE
  • New for 2004

    Publication Year: 2004, Page(s): 288
    Request permission for commercial reuse | PDF file iconPDF (67 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