IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 6 • June 2002

Filter Results

Displaying Results 1 - 15 of 15
  • Call for papers

    Publication Year: 2002, Page(s): 721
    Request permission for commercial reuse | PDF file iconPDF (187 KB)
    Freely Available from IEEE
  • Imaged document text retrieval without OCR

    Publication Year: 2002, Page(s):838 - 844
    Cited by:  Papers (47)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (966 KB) | HTML iconHTML

    We propose a method for text retrieval from document images without the use of OCR. Documents are segmented into character objects. Image features, namely the vertical traverse density (VTD) and horizontal traverse density (HTD), are extracted. An n-gram-based document vector is constructed for each document based on these features. Text similarity between documents is then measured by calculating... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Inference of segmented overlapping surfaces from binocular stereo

    Publication Year: 2002, Page(s):824 - 837
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1923 KB) | HTML iconHTML

    Presents an integrated approach to the derivation of scene descriptions from a pair of stereo images, where the steps of feature correspondence and surface reconstruction are addressed within the same framework. Special attention is given to the development of a methodology with general applicability. In order to handle the issues of noise, lack of image features, surface discontinuities and regio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Curvature-augmented tensor voting for shape inference from noisy 3D data

    Publication Year: 2002, Page(s):858 - 864
    Cited by:  Papers (43)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1150 KB) | HTML iconHTML

    Improves the basic tensor voting formalism to infer the sign and direction of principal curvatures at each input site from noisy 3D data. Unlike most previous approaches, no local surface fitting, partial derivative computation, nor oriented normal vector recovery is performed in our method. These approaches are known to be noise-sensitive, since accurate partial derivative information is often re... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optical character recognition for cursive handwriting

    Publication Year: 2002, Page(s):801 - 813
    Cited by:  Papers (65)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1265 KB) | HTML iconHTML

    A new analytic scheme, which uses a sequence of image segmentation and recognition algorithms, is proposed for the off-line cursive handwriting recognition problem. First, some global parameters, such as slant angle, baselines, stroke width and height, are estimated. Second, a segmentation method finds character segmentation paths by combining gray-scale and binary information. Third, a hidden Mar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fundamental relationship between bilateral filtering, adaptive smoothing, and the nonlinear diffusion equation

    Publication Year: 2002, Page(s):844 - 847
    Cited by:  Papers (237)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (406 KB) | HTML iconHTML

    In this paper, the relationship between bilateral filtering and anisotropic diffusion is examined. The bilateral filtering approach represents a large class of nonlinear digital image filters. We first explore the connection between anisotropic diffusion and adaptive smoothing, and then the connection between adaptive smoothing and bilateral filtering. Previously, adaptive smoothing was considered... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adjusting shape parameters using model-based optical flow residuals

    Publication Year: 2002, Page(s):814 - 823
    Cited by:  Papers (13)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1020 KB) | HTML iconHTML

    We present a method for estimating the shape of a deformable model using the least-squares residuals from a model-based optical flow computation. This method is built on top of an estimation framework using optical flow and image features, where optical flow affects only the motion parameters of the model. Using the results of this computation, our new method adjusts all of the parameters so that ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive image segmentation by combining photometric invariant region and edge information

    Publication Year: 2002, Page(s):848 - 852
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (379 KB) | HTML iconHTML

    An adaptive image segmentation scheme is proposed employing the Delaunay triangulation for image splitting. The tessellation grid of the Delaunay triangulation is adapted to the semantics of the image data by combining region and edge information. To achieve robustness against imaging conditions (e.g. shading, shadows, illumination and highlights), photometric invariant similarity measures and edg... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improving the clustering performance of the scanning n-tuple method by using self-supervised algorithms to introduce subclasses

    Publication Year: 2002, Page(s):722 - 733
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (664 KB) | HTML iconHTML

    The scanning n-tuple technique (as introduced by Lucas and Amiri, 1996) is studied in pattern recognition tasks, with emphasis placed on methods that improve its recognition performance. We remove potential edge effect problems and optimize the parameters of the scanning n-tuple method with respect to memory requirements, processing speed and recognition accuracy for a case study task. Next, we re... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Maximum-likelihood image matching

    Publication Year: 2002, Page(s):853 - 857
    Cited by:  Papers (39)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (413 KB) | HTML iconHTML

    Image-matching applications, such as tracking and stereo, commonly use the sum-of-squared-difference (SSD) measure to determine the best match. However, this measure is sensitive to outliers and is not robust to template variations. Alternative measures have also been proposed that are more robust to these issues. We improve upon these using a probabilistic formulation for image matching in terms ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Density-based multiscale data condensation

    Publication Year: 2002, Page(s):734 - 747
    Cited by:  Papers (64)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (778 KB) | HTML iconHTML

    A problem gaining interest in pattern recognition applied to data mining is that of selecting a small representative subset from a very large data set. In this article, a nonparametric data reduction scheme is suggested. It attempts to represent the density underlying the data. The algorithm selects representative points in a multiscale fashion which is novel from existing density-based approaches... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognizing imprecisely localized, partially occluded, and expression variant faces from a single sample per class

    Publication Year: 2002, Page(s):748 - 763
    Cited by:  Papers (432)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (866 KB) | HTML iconHTML

    The classical way of attempting to solve the face (or object) recognition problem is by using large and representative data sets. In many applications, though, only one sample per class is available to the system. In this contribution, we describe a probabilistic approach that is able to compensate for imprecisely localized, partially occluded, and expression-variant faces even when only one singl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Face recognition using line edge map

    Publication Year: 2002, Page(s):764 - 779
    Cited by:  Papers (224)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (705 KB) | HTML iconHTML

    The automatic recognition of human faces presents a significant challenge to the pattern recognition research community. Typically, human faces are very similar in structure with minor differences from person to person. They are actually within one class of "human face". Furthermore, lighting conditions change, while facial expressions and pose variations further complicate the face recognition ta... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Principal manifolds and probabilistic subspaces for visual recognition

    Publication Year: 2002, Page(s):780 - 788
    Cited by:  Papers (159)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (604 KB) | HTML iconHTML

    Investigates the use of linear and nonlinear principal manifolds for learning low-dimensional representations for visual recognition. Several leading techniques - principal component analysis (PCA), independent component analysis (ICA) and nonlinear kernel PCA (KPCA) - are examined and tested in a visual recognition experiment using 1,800+ facial images from the "FERET" (FacE REcognition Technolog... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Use of lexicon density in evaluating word recognizers

    Publication Year: 2002, Page(s):789 - 800
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (529 KB) | HTML iconHTML

    We have developed the notion of lexicon density as a metric to measure the expected accuracy of handwritten word recognizers. Thus far, researchers have used the size of the lexicon as a gauge for the difficulty of the handwritten word recognition task. For example, the literature mentions recognizers with accuracies for lexicons of sizes 10, 100, 1000, and so forth, implying that the difficulty 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