By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 8 • Aug 1999

Filter Results

Displaying Results 1 - 14 of 14
  • An HMM-based approach for off-line unconstrained handwritten word modeling and recognition

    Publication Year: 1999, Page(s):752 - 760
    Cited by:  Papers (120)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (224 KB)

    Describes a hidden Markov model-based approach designed to recognize off-line unconstrained handwritten words for large vocabularies. After preprocessing, a word image is segmented into letters or pseudoletters and represented by two feature sequences of equal length, each consisting of an alternating sequence of shape-symbols and segmentation-symbols, which are both explicitly modeled. The word m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A computational model of view degeneracy

    Publication Year: 1999, Page(s):673 - 689
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (732 KB)

    We quantify the observation by Kender and Freudenstein (1987) that degenerate views occupy a significant fraction of the viewing sphere surrounding an object. For a perspective camera geometry, we introduce a computational model that can be used to estimate the probability that a view degeneracy will occur in a random view of a polyhedral object. For a typical recognition system parameterization, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Indexing of technical line drawing databases

    Publication Year: 1999, Page(s):737 - 751
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (384 KB)

    Image indexing, namely, the problem of retrieving content information from images in response to queries, is a key problem underlying the operations in image databases. We present a method of indexing for 3D object queries in a database of a class of images called technical line drawings. Indexing is achieved as a combination of query-specific region selection and object recognition. The selection... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Linear N-point camera pose determination

    Publication Year: 1999, Page(s):774 - 780
    Cited by:  Papers (233)  |  Patents (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (280 KB)

    The determination of camera position and orientation from known correspondences of 3D reference points and their images is known as pose estimation in computer vision and space resection in photogrammetry. It is well-known that from three corresponding points there are at most four algebraic solutions. Less appears to be known about the cases of four and five corresponding points. We propose a fam... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • How should we represent faces for automatic recognition?

    Publication Year: 1999, Page(s):725 - 736
    Cited by:  Papers (67)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (848 KB)

    We describe results obtained from a testbed used to investigate different codings for automatic face recognition. An eigenface coding of shape-free faces using manually located landmarks was more effective than the corresponding coding of correctly shaped faces. Configuration also proved an effective method of recognition, with rankings given to incorrect matches relatively uncorrelated with those... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A learning-based prediction-and-verification segmentation scheme for hand sign image sequence

    Publication Year: 1999, Page(s):798 - 804
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1120 KB)

    We present a prediction-and-verification segmentation scheme using attention images from multiple fixations. A major advantage of this scheme is that it can handle a large number of different deformable objects presented in complex backgrounds. The scheme is also relatively efficient. The system was tested to segment hands in sequences of intensity images, where each sequence represents a hand sig... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integral ratio: a new class of global thresholding techniques for handwriting images

    Publication Year: 1999, Page(s):761 - 768
    Cited by:  Papers (61)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (568 KB)

    We propose a class of histogram based global thresholding techniques called integral ratio. They are designed to threshold gray-scale handwriting images and separate the handwriting from the background. The following tight requirements must be met: 1) all the details of the handwriting are to be retained, 2) the writing paper used may contain strong colored and/or patterned background which must b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shape-from-shading: a survey

    Publication Year: 1999, Page(s):690 - 706
    Cited by:  Papers (590)  |  Patents (44)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1544 KB)

    Since the first shape-from-shading (SFS) technique was developed by Horn in the early 1970s, many different approaches have emerged. In this paper, six well-known SFS algorithms are implemented and compared. The performance of the algorithms was analyzed on synthetic images using mean and standard deviation of depth (Z) error, mean of surface gradient (p, q) error, and CPU timing. Each algorithm w... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Making use of contradictory behavior information in qualitative reasoning

    Publication Year: 1999, Page(s):781 - 786
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (172 KB)

    We present a technique for automatically determining certain pairs of qualitative simulation predictions to be mutually contradictory. This leads the simulator to produce more informative outputs, which results in improved performance in reasoning tasks like diagnosis, model revision, and deletion of spurious “timelines” containing the input state View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cross-weighted moments and affine invariants for image registration and matching

    Publication Year: 1999, Page(s):804 - 814
    Cited by:  Papers (42)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (964 KB)

    A framework for deriving a class of new global affine invariants for both object matching and positioning based on a novel concept of cross-weighted moments with fractional weights is presented. The fractional weight factor allows for a more flexible range to balance between the capability to discriminate between objects that differ only in small shape details and the sensitivity of small shape de... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust rotation angle estimator

    Publication Year: 1999, Page(s):768 - 773
    Cited by:  Papers (26)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (500 KB)

    The conventional method of estimating the rotation angle of a pattern using the principal axes is not suitable for circular symmetric patterns since their eigenvalues are similar in both directions. In the paper, a robust method of estimating a rotation angle using the phase information of Zernike moments is presented. The experimental results show that the proposed method estimates the rotation a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stratified self-calibration with the modulus constraint

    Publication Year: 1999, Page(s):707 - 724
    Cited by:  Papers (82)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1852 KB)

    In computer vision and especially for 3D reconstruction, one of the key issues is the retrieval of the calibration parameters of the camera. These are needed to obtain metric information about the scene from the camera. Often these parameters are obtained through cumbersome calibration procedures. There is a way to avoid explicit calibration of the camera. Self-calibration is based on finding the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast decomposition of digital curves into polygons using the Haar transform

    Publication Year: 1999, Page(s):786 - 790
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (184 KB)

    The perimeters of features in digital images are decomposed into sets of straight lines using the Haar transform. The Haar basis functions preserve sharp changes in direction along the perimeter while still allowing smoothing. The coefficients of the Haar transform are simply related to the error between the polygonal decomposition and the true perimeter. The Haar transform can be calculated effic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiprimitive segmentation of planar curves-a two-level breakpoint classification and tuning approach

    Publication Year: 1999, Page(s):791 - 797
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (296 KB)

    A breakpoint classification and tuning approach is proposed for the multiprimitive segmentation of planar curves, and cockhead-like graph is suggested to evaluate the multiprimitive segmentation algorithms. The breakpoints are divided into corners and smooth joints and the types of the segments on both sides of a breakpoint are identified. Then, a joint tuning procedure is exercised to merge/split... 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