By Topic

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Issue 12 • Date Dec. 2004

Filter Results

Displaying Results 1 - 20 of 20
  • [Front cover]

    Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (128 KB)  
    Freely Available from IEEE
  • [Inside front cover]

    Page(s): c2
    Save to Project icon | Request Permissions | PDF file iconPDF (75 KB)  
    Freely Available from IEEE
  • Shape-based recognition of wiry objects

    Page(s): 1537 - 1552
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2272 KB) |  | HTML iconHTML  

    We present an approach to the recognition of complex-shaped objects in cluttered environments based on edge information. We first use example images of a target object in typical environments to train a classifier cascade that determines whether edge pixels in an image belong to an instance of the desired object or the clutter. Presented with a novel image, we use the cascade to discard clutter edge pixels and group the object edge pixels into overall detections of the object. The features used for the edge pixel classification are localized, sparse edge density operations. Experiments validate the effectiveness of the technique for recognition of a set of complex objects in a variety of cluttered indoor scenes under arbitrary out-of-image-plane rotation. Furthermore, our experiments suggest that the technique is robust to variations between training and testing environments and is efficient at runtime. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semisupervised learning of classifiers: theory, algorithms, and their application to human-computer interaction

    Page(s): 1553 - 1566
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (976 KB) |  | HTML iconHTML  

    Automatic classification is one of the basic tasks required in any pattern recognition and human computer interaction application. In this paper, we discuss training probabilistic classifiers with labeled and unlabeled data. We provide a new analysis that shows under what conditions unlabeled data can be used in learning to improve classification performance. We also show that, if the conditions are violated, using unlabeled data can be detrimental to classification performance. We discuss the implications of this analysis to a specific type of probabilistic classifiers, Bayesian networks, and propose a new structure learning algorithm that can utilize unlabeled data to improve classification. Finally, we show how the resulting algorithms are successfully employed in two applications related to human-computer interaction and pattern recognition: facial expression recognition and face detection. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Frequency domain formulation of active parametric deformable models

    Page(s): 1568 - 1578
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (840 KB) |  | HTML iconHTML  

    Active deformable models are simple tools, very popular in computer vision and computer graphics, for solving ill-posed problems or mimic real physical systems. The classical formulation is given in the spatial domain, the motor of the procedure is a second-order linear system, and rigidity and elasticity are the basic parameters for its characterization. This paper proposes a novel formulation based on a frequency-domain analysis: the internal energy functional and the Lagrange minimization are performed entirely in the frequency domain, which leads to a simple formulation and design. The frequency-based implementation offers important computational savings in comparison to the original one, a feature that is improved by the efficient hardware and software computation of the FFT algorithm. This new formulation focuses on the stiffness spectrum, allowing the possibility of constructing deformable models apart from the elasticity and rigidity-based original formulation. Simulation examples validate the theoretical results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection of image structures using the Fisher information and the Rao metric

    Page(s): 1579 - 1589
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (568 KB) |  | HTML iconHTML  

    In many detection problems, the structures to be detected are parameterized by the points of a parameter space. If the conditional probability density function for the measurements is known, then detection can be achieved by sampling the parameter space at a finite number of points and checking each point to see if the corresponding structure is supported by the data. The number of samples and the distances between neighboring samples are calculated using the Rao metric on the parameter space. The Rao metric is obtained from the Fisher information which is, in turn, obtained from the conditional probability density function. An upper bound is obtained for the probability of a false detection. The calculations are simplified in the low noise case by making an asymptotic approximation to the Fisher information. An application to line detection is described. Expressions are obtained for the asymptotic approximation to the Fisher information, the volume of the parameter space, and the number of samples. The time complexity for line detection is estimated. An experimental comparison is made with a Hough transform-based method for detecting lines. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition by symmetry derivatives and the generalized structure tensor

    Page(s): 1590 - 1605
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1086 KB) |  | HTML iconHTML  

    We suggest a set of complex differential operators that can be used to produce and filter dense orientation (tensor) fields for feature extraction, matching, and pattern recognition. We present results on the invariance properties of these operators, that we call symmetry derivatives. These show that, in contrast to ordinary derivatives, all orders of symmetry derivatives of Gaussians yield a remarkable invariance: they are obtained by replacing the original differential polynomial with the same polynomial, but using ordinary coordinates x and y corresponding to partial derivatives. Moreover, the symmetry derivatives of Gaussians are closed under the convolution operator and they are invariant to the Fourier transform. The equivalent of the structure tensor, representing and extracting orientations of curve patterns, had previously been shown to hold in harmonic coordinates in a nearly identical manner. As a result, positions, orientations, and certainties of intricate patterns, e.g., spirals, crosses, parabolic shapes, can be modeled by use of symmetry derivatives of Gaussians with greater analytical precision as well as computational efficiency. Since Gaussians and their derivatives are utilized extensively in image processing, the revealed properties have practical consequences for local orientation based feature extraction. The usefulness of these results is demonstrated by two applications: 1) tracking cross markers in long image sequences from vehicle crash tests and 2) alignment of noisy fingerprints. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A coarse-to-fine strategy for multiclass shape detection

    Page(s): 1606 - 1621
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (920 KB) |  | HTML iconHTML  

    Multiclass shape detection, in the sense of recognizing and localizing instances from multiple shape classes, is formulated as a two-step process in which local indexing primes global interpretation. During indexing a list of instantiations (shape identities and poses) is compiled, constrained only by no missed detections at the expense of false positives. Global information, such as expected relationships among poses, is incorporated afterward to remove ambiguities. This division is motivated by computational efficiency. In addition, indexing itself is organized as a coarse-to-fine search simultaneously in class and pose. This search can be interpreted as successive approximations to likelihood ratio tests arising from a simple ("naive Bayes") statistical model for the edge maps extracted from the original images. The key to constructing efficient "hypothesis tests" for multiple classes and poses is local ORing; in particular, spread edges provide imprecise but common and locally invariant features. Natural tradeoffs then emerge between discrimination and the pattern of spreading. These are analyzed mathematically within the model-based framework and the whole procedure is illustrated by experiments in reading license plates. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The visual hull of smooth curved objects

    Page(s): 1622 - 1632
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (912 KB) |  | HTML iconHTML  

    The visual hull is a geometric entity that relates the shape of an object to its silhouettes or shadows. This paper develops the theory of the visual hull of generic smooth objects. We show that the visual hull can be constructed using surfaces which partition the viewpoint space of the aspect graph of the object. The surfaces are those generated by the visual events tangent crossing and triple point. An analysis based on the shape of the object at the tangency points of these surfaces allows pruning away many surfaces and patches not relevant to the construction. An algorithm for computing the visual hull is outlined. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Globally convergent autocalibration using interval analysis

    Page(s): 1633 - 1638
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (472 KB) |  | HTML iconHTML  

    We address the problem of autocalibration of a moving camera with unknown constant intrinsic parameters. Existing autocalibration techniques use numerical optimization algorithms whose convergence to the correct result cannot be guaranteed, in general. To address this problem, we have developed a method where an interval branch-and-bound method is employed for numerical minimization. Thanks to the properties of interval analysis this method converges to the global solution with mathematical certainty and arbitrary accuracy and the only input information it requires from the user are a set of point correspondences and a search interval. The cost function is based on the Huang-Faugeras constraint of the essential matrix. A recently proposed interval extension based on Bernstein polynomial forms has been investigated to speed up the search for the solution. Finally, experimental results are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Correlation filter: an accurate approach to detect and locate low contrast character strings in complex table environment

    Page(s): 1639 - 1644
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (848 KB) |  | HTML iconHTML  

    Correlation has been used extensively in object detection field. In this paper, two kinds of correlation filters, minimum average correlation energy (MACE) and extended maximum average correlation height (EMACH), are applied as adaptive shift locators to detect and locate smudgy character strings in complex tabular color flight coupon images. These strings in irregular tabular coupon are computer-printed characters but of low contrast and could be shifted out of the table so that we cannot detect and locate them using traditional algorithms. In our experiment, strings are extracted in the preprocessing phase by removing background and then based on geometric information, two correlation filters are applied to locate expected fields. We compare results from two correlation filters and demonstrate that this algorithm is a high accurate approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Eigenregions for image classification

    Page(s): 1645 - 1649
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (624 KB) |  | HTML iconHTML  

    For certain databases and classification tasks, analyzing images based on region features instead of image features results in more accurate classifications. We introduce eigenregions, which are geometrical features that encompass area, location, and shape properties of an image region, even if the region is spatially incoherent. Eigenregions are calculated using principal component analysis (PCA). On a database of 77,000 different regions obtained through the segmentation of 13,500 real-scene photographic images taken by nonprofessional, eigenregions improved the detection of localized image classes by a noticeable amount. Additionally, eigenregions allow us to prove that the largest variance in natural image region geometry is due to its area and not to shape or position. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spherical diffusion for 3D surface smoothing

    Page(s): 1650 - 1654
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (308 KB) |  | HTML iconHTML  

    A diffusion-based approach to surface smoothing is presented. Surfaces are represented as scalar functions defined on the sphere. The approach is equivalent to Gaussian smoothing on the sphere and is computationally efficient since it does not require iterative smoothing. Furthermore, it does not suffer from the well-known shrinkage problem. Evolution of important shape features (parabolic curves) under diffusion is demonstrated. A nonlinear modification of the diffusion process is introduced in order to improve smoothing behavior of elongated and poorly centered objects. View full abstract»

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

    Page(s): 1655 - 1676
    Save to Project icon | Request Permissions | PDF file iconPDF (166 KB)  
    Freely Available from IEEE
  • [Advertisement]

    Page(s): 1677
    Save to Project icon | Request Permissions | PDF file iconPDF (373 KB)  
    Freely Available from IEEE
  • [Advertisement]

    Page(s): 1678
    Save to Project icon | Request Permissions | PDF file iconPDF (663 KB)  
    Freely Available from IEEE
  • [Advertisement]

    Page(s): 1679
    Save to Project icon | Request Permissions | PDF file iconPDF (513 KB)  
    Freely Available from IEEE
  • [Advertisement]

    Page(s): 1680
    Save to Project icon | Request Permissions | PDF file iconPDF (306 KB)  
    Freely Available from IEEE
  • TPAMI Information for authors

    Page(s): c3
    Save to Project icon | Request Permissions | PDF file iconPDF (75 KB)  
    Freely Available from IEEE
  • [Back cover]

    Page(s): c4
    Save to Project icon | Request Permissions | PDF file iconPDF (128 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