By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 3 • Date March 1989

Filter Results

Displaying Results 1 - 13 of 13
  • Comments on approximating discrete probability distributions with dependence trees

    Publication Year: 1989, Page(s):333 - 335
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (241 KB)

    C.K. Chow and C.N. Liu (1968) introduced the notion of three dependence to approximate a kth-order probability distribution. More recently, A.K.C. Wong and C.C. Wang (1977) proposed a different product approximation. The present authors show that the tree dependence approximation suggested by Chow and Liu can be derived by minimizing an upper bound of the Bayes error rate under certain assumptions... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Line fitting in a noisy image

    Publication Year: 1989, Page(s):325 - 329
    Cited by:  Papers (27)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (404 KB)

    The conventional least-squared-distance method of fitting a line to a set of data points is unreliable when the amount of random noise in the input (such as an image) is significant compared with the amount of data correlated to the line itself. Points which are far away from the line (outliers) are usually just noise, but they contribute the most to the distance averaging, skewing the line from i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Polymorphic-torus architecture for computer vision

    Publication Year: 1989, Page(s):233 - 243
    Cited by:  Papers (83)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1100 KB)

    A massively parallel fine-grained SIMD (single-instruction multi-data-stream) computer for machine vision computations is described. The architecture features a polymorphic-torus network which inserts an individually controllable switch into every node of the two-dimensional torus such that the network is dynamically reconfigurable to match the algorithm. Reconfiguration is accomplished by circuit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical construction of orientation and velocity selective filters

    Publication Year: 1989, Page(s):315 - 325
    Cited by:  Papers (51)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1856 KB)

    As a step towards the early measurement of visual primitives, the authors outline design criteria for the extraction of orientation and velocity information, and present a variety of tools useful in the construction of simple linear filters. A hierarchical parallel-processing scheme is used in which nodes compute a weighted sum of inputs from within a small spatio-temporal neighborhood. The result... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An EREW PRAM algorithm for image component labeling

    Publication Year: 1989, Page(s):258 - 262
    Cited by:  Papers (25)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (552 KB)

    An important midlevel task for computer vision is addressed. The problem consists of labeling connected components in N1/2 ×N2/2 binary images. This task can be solved with parallel computers by using a simple and novel algorithm. The parallel computing model used is a synchronous fine-grained shared-memory model where only one processor can read from ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • HBA vision architecture: built and benchmarked

    Publication Year: 1989, Page(s):227 - 232
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (492 KB)

    A description is given of the hierarchical bus architecture (HBA), its programming environment, and algorithmic benchmarks. For local neighborhood operations the HBA implements the Apply programming model. Apply enables the vision programmer to write image-to-image transformations without regard to the details of parallelism, looping, of boundary conditions. The HBA supports all levels of vision o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dimensionality-reduction using connectionist networks

    Publication Year: 1989, Page(s):304 - 314
    Cited by:  Papers (28)  |  Patents (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (912 KB)

    A method is presented for using connectionist networks of simple computing elements to discover a particular type of constraint in multidimensional data. Suppose that some data source provides samples consisting of n-dimensional feature-vectors, but that this data all happens to lie on an m-dimensional surface embedded in the n-dimensional feature space. Then occurrences... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D Euclidean versus 2D non-Euclidean: two approaches to 3D recovery from images

    Publication Year: 1989, Page(s):329 - 332
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (448 KB)

    Methods of 3D recovery in computer vision for computing the shape and motion of an object from projected images when an object model is available are classified into two types: the 3D Euclidean approach, which is based on geometrical constraints in 3D Euclidean space, and the 2D non-Euclidean space. Implications of these two approaches are discussed, and some illustrating examples are presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Algorithmic techniques for computer vision on a fine-grained parallel machine

    Publication Year: 1989, Page(s):244 - 257
    Cited by:  Papers (52)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1300 KB)

    The authors describe several fundamentally useful primitive operations and routines and illustrate their usefulness in a wide range of familiar version processes. These operations are described in terms of a vector machine model of parallel computation. They use a parallel vector model because vector models can be mapped onto a wide range of architectures. They also describe implementing these pri... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computing the Hough transform on a scan line array processor [image processing]

    Publication Year: 1989, Page(s):262 - 265
    Cited by:  Papers (35)  |  Patents (25)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (372 KB)

    A parallel algorithm for a line-finding Hough transform that runs on a linearly connected, SIMD (single-instruction, multiple-data-stream) vector of processors is described. The authors show that a high-precision transform, usually considered to be an expensive global operation, can be performed efficiently, in two to three times real time, with only local, communication on a long vector. The algo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interpretation of image flow: a spatio-temporal approach

    Publication Year: 1989, Page(s):266 - 278
    Cited by:  Papers (33)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1080 KB)

    A general formulation is described for the interpretation of image flow. In the framework of this formulation, computational methods have been derived for image flow interpretation for many important cases, including simple cases of nonrigid and nonuniform motions. It is possible to derive computational methods for other situations not considered explicitly. The formulation is general in that it i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition and shape synthesis of 3-D objects based on attributed hypergraphs

    Publication Year: 1989, Page(s):279 - 290
    Cited by:  Papers (51)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (972 KB)

    A computer vision system is presented for shape synthesis and recognition of three-dimensional objects using an attributed hypergraph representation. The vision system is capable of: (1) constructing an attributed hypergraph representation (AHR) based on the information extracted from an image with range data; (2) synthesizing several AHRs obtained from various views of an object to form a complet... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Three-dimensional ultrasonic vision for robotic applications

    Publication Year: 1989, Page(s):291 - 303
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (848 KB)

    Considers a vision system that uses the echo of a transmitted ultrasonic pulse as the basis for identifying objects. The return of a single pulse from an object generates a three-dimensional acoustical characteristic signature across the aperture of a receiving antenna which can be directly used for object identification. Thus, there is no need to reproduce an accurate visual representation to rec... 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
David A. Forsyth
University of Illinois
e-mail: daf@illinois.edu