Scheduled System Maintenance
On Tuesday, September 26, IEEE Xplore will undergo scheduled maintenance from 1:00-4:00 PM ET.
During this time, there may be intermittent impact on performance. We apologize for any inconvenience.

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 5 • May 2004

Filter Results

Displaying Results 1 - 17 of 17
  • IEEE Transactions on Pattern Analysis and Machine Intelligence - Cover

    Publication Year: 2004, Page(s):0_1 - 673
    Request permission for commercial reuse | PDF file iconPDF (279 KB)
    Freely Available from IEEE
  • IEEE Computer Society's - Staff List

    Publication Year: 2004, Page(s): 0_2
    Request permission for commercial reuse | PDF file iconPDF (223 KB)
    Freely Available from IEEE
  • Introduction of new Associate Editors

    Publication Year: 2004, Page(s): 529
    Request permission for commercial reuse | PDF file iconPDF (205 KB)
    Freely Available from IEEE
  • Learning to detect natural image boundaries using local brightness, color, and texture cues

    Publication Year: 2004, Page(s):530 - 549
    Cited by:  Papers (928)  |  Patents (43)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5245 KB) | HTML iconHTML

    The goal of this work is to accurately detect and localize boundaries in natural scenes using local image measurements. We formulate features that respond to characteristic changes in brightness, color, and texture associated with natural boundaries. In order to combine the information from these features in an optimal way, we train a classifier using human labeled images as ground truth. The outp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition of shapes by editing their shock graphs

    Publication Year: 2004, Page(s):550 - 571
    Cited by:  Papers (356)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4855 KB) | HTML iconHTML

    This paper presents a novel framework for the recognition of objects based on their silhouettes. The main idea is to measure the distance between two shapes as the minimum extent of deformation necessary for one shape to match the other. Since the space of deformations is very high-dimensional, three steps are taken to make the search practical: 1) define an equivalence class for shapes based on s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Gabor-based kernel PCA with fractional power polynomial models for face recognition

    Publication Year: 2004, Page(s):572 - 581
    Cited by:  Papers (285)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (919 KB) | HTML iconHTML

    This paper presents a novel Gabor-based kernel principal component analysis (PCA) method by integrating the Gabor wavelet representation of face images and the kernel PCA method for face recognition. Gabor wavelets first derive desirable facial features characterized by spatial frequency, spatial locality, and orientation selectivity to cope with the variations due to illumination and facial expre... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Algorithms for matching 3D line sets

    Publication Year: 2004, Page(s):582 - 593
    Cited by:  Papers (18)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1233 KB) | HTML iconHTML

    Matching two sets of lines is a basic tool that has applications in many computer vision problems such as scene registration, object recognition, motion estimation, and others. Line sets may be composed of infinitely long lines or finite length line segments. Depending on line lengths, three basic cases arise in matching sets of lines: 1) finite-finite, 2) finite-infinite, and 3) infinite-infinite... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • First order augmentation to tensor voting for boundary inference and multiscale analysis in 3D

    Publication Year: 2004, Page(s):594 - 611
    Cited by:  Papers (28)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3034 KB) | HTML iconHTML

    Most computer vision applications require the reliable detection of boundaries. In the presence of outliers, missing data, orientation discontinuities, and occlusion, this problem is particularly challenging. We propose to address it by complementing the tensor voting framework, which was limited to second order properties, with first order representation and voting. First order voting fields and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Top-down induction of model trees with regression and splitting nodes

    Publication Year: 2004, Page(s):612 - 625
    Cited by:  Papers (24)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1530 KB) | HTML iconHTML

    Model trees are an extension of regression trees that associate leaves with multiple regression models. In this paper, a method for the data-driven construction of model trees is presented, namely, the stepwise model tree induction (SMOTI) method. Its main characteristic is the induction of trees with two types of nodes: regression nodes, which perform only straight-line regression, and splitting ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A statistical model for contours in images

    Publication Year: 2004, Page(s):626 - 638
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1521 KB) | HTML iconHTML

    In this paper, we describe a statistical model for the gradient vector field of the gray level in images validated by different experiments. Moreover, we present a global constrained Markov model for contours in images that uses this statistical model for the likelihood. Our model is amenable to an iterative conditional estimation (ICE) procedure for the estimation of the parameters; our model als... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Separation of diffuse and specular components of surface reflection by use of polarization and statistical analysis of images

    Publication Year: 2004, Page(s):639 - 647
    Cited by:  Papers (51)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (847 KB) | HTML iconHTML

    The image of an opaque object is created by observing the reflection of the light incident on its surface. The dichromatic reflection model describes the surface reflection as the sum of two components, diffuse and specular terms. The specular reflection component is usually strong in its intensity and polarized significantly compared to the diffuse components. On the other hand, the intensity of ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Invariant fitting of two view geometry

    Publication Year: 2004, Page(s):648 - 650
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (246 KB) | HTML iconHTML

    This paper describes an extension of Bookstein's and Sampson's methods, for fitting conics, to the determination of epipolar geometry, both in the calibrated case, where the Essential matrix E is to be determined or in the uncalibrated case, where we seek the fundamental matrix F. We desire that the fitting of the relation be invariant to Euclidean transformations of the image, and show that there... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recursive unsupervised learning of finite mixture models

    Publication Year: 2004, Page(s):651 - 656
    Cited by:  Papers (122)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (670 KB) | HTML iconHTML

    There are two open problems when finite mixture densities are used to model multivariate data: the selection of the number of components and the initialization. In this paper, we propose an online (recursive) algorithm that estimates the parameters of the mixture and that simultaneously selects the number of components. The new algorithm starts with a large number of randomly initialized component... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive quasiconformal kernel nearest neighbor classification

    Publication Year: 2004, Page(s):656 - 661
    Cited by:  Papers (29)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (563 KB) | HTML iconHTML

    Nearest neighbor classification assumes locally constant class conditional probabilities. This assumption becomes invalid in high dimensions due to the curse-of-dimensionality. Severe bias can be introduced under these conditions when using the nearest neighbor rule. We propose an adaptive nearest neighbor classification method to try to minimize bias. We use quasiconformal transformed kernels to ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimal linear representations of images for object recognition

    Publication Year: 2004, Page(s):662 - 666
    Cited by:  Papers (51)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (471 KB) | HTML iconHTML

    Although linear representations are frequently used in image analysis, their performances are seldom optimal in specific applications. This paper proposes a stochastic gradient algorithm for finding optimal linear representations of images for use in appearance-based object recognition. Using the nearest neighbor classifier, a recognition performance function is specified and linear representation... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • VC-dimension of exterior visibility

    Publication Year: 2004, Page(s):667 - 671
    Cited by:  Papers (20)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (351 KB) | HTML iconHTML

    In this paper, we study the Vapnik-Chervonenkis (VC)-dimension of set systems arising in 2D polygonal and 3D polyhedral configurations where a subset consists of all points visible from one camera. In the past, it has been shown that the VC-dimension of planar visibility systems is bounded by 23 if the cameras are allowed to be anywhere inside a polygon without holes. Here, we consider the case of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TPAMI: Information for authors

    Publication Year: 2004, Page(s): 672
    Request permission for commercial reuse | PDF file iconPDF (223 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
Sven Dickinson
University of Toronto
e-mail: sven@cs.toronto.edu