IEE Proceedings - Vision, Image and Signal Processing

Issue 6 • Dec 1998

Filter Results

Displaying Results 1 - 8 of 8
  • New windowing techniques for variable-size block motion compensation

    Publication Year: 1998, Page(s):399 - 407
    Cited by:  Papers (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (916 KB)

    The conventional overlapped block motion compensation (OBMC) technique, although effective in reducing the blocking effect for fixed-size partitioned frames, cannot be readily used for a frame partitioned region-wise or using variable-size blocks. The generalised OBMC (GOBMC) method, even though generally applicable, is not very effective in reducing the blocking effect and prediction error. Two w... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • P pattern recognition based on a probabilistic RAM net using n-tuple input mapping

    Publication Year: 1998, Page(s):415 - 420
    Cited by:  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (640 KB)

    A multilayer digital neural network, based on the probabilistic random access memory (pRAM), is used as a P pattern classifier system. This network presents an elaborate implementation of the n-tuple technique, which has mostly been used for pattern recognition (Bledsoe and Browning, 1959). The network's main properties, discrimination and generalisation, are discussed as a function of the pRAM co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Family of generalised multi-polarity complex Hadamard transforms

    Publication Year: 1998, Page(s):371 - 378
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (716 KB)

    A family of generalised complex Hadamard transforms using the concept of polarity is introduced. Forward and inverse transformation kernels and methods of recursive generation of transform matrices using Kronecker products of elementary matrices are shown. Mutual relationships among transform matrices and spectra for arbitrary polarities are presented. Efficient ways of calculating spectra for log... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Complexity-constrained best-basis wavelet packet algorithm for image compression

    Publication Year: 1998, Page(s):391 - 398
    Cited by:  Papers (3)  |  Patents (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (1016 KB)

    The concept of adapted waveform analysis using a best-basis selection out of a predefined library of wavelet packet (WP) bases allows an efficient image representation for the purpose of compression. Image coding methods based on the best-basis WP representation have shown significant coding gains for some image classes compared with methods using a fixed dyadic structured wavelet basis, at the ex... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Novel scheme for low-power classified vector quantisation image coding

    Publication Year: 1998, Page(s):408 - 414
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (776 KB)

    A novel scheme for low-power image coding and decoding based on classified vector quantisation is presented. The main idea is the replacement of the memory accesses to large background memories (most power-consuming operations), by arithmetic and/or application-specific computations. Specifically, the proposed image coding scheme uses small sub-codebooks to reduce the memory requirements and memor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A posteriori real-time recurrent learning schemes for a recurrent neural network based nonlinear predictor

    Publication Year: 1998, Page(s):365 - 370
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (556 KB)

    Recurrent neural networks (RNNs) are well established for the nonlinear and nonstationary signal prediction paradigm. Appropriate learning algorithms, such as the real-time recurrent learning (RTRL) algorithm, have been developed for that purpose. However, little is known about the RNN time-management policy. Here, insight is provided into the time-management of the RNN, and an a posteriori approa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Quality enhancement of sinusoidal transform vocoders

    Publication Year: 1998, Page(s):379 - 383
    Cited by:  Papers (1)  |  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (444 KB)

    The authors present quality enhancement of sinusoidal transform coders (STCs) via the development of parametric models. The benefits of the Bark spectrum are explored for use in the design of perceptual coding of the sine-wave amplitudes. According to the results, the proposed approach provides a uniform perceptual fit across the spectrum. To enhance the accuracy of phase representation, noncausal... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmental probability distribution model approach for isolated Mandarin syllable recognition

    Publication Year: 1998, Page(s):384 - 390
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (652 KB)

    A segmental probability distribution model (SPDM) approach is proposed for fast and accurate recognition of isolated Mandarin syllables. Instead of the conventional frame-based approach such as the hidden Markov model (HMM), the model matching process in the proposed SPDM is evaluated segment-by-segment based on information-theoretic distance measurements. The training and recognition procedures f... View full abstract»

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

Aims & Scope

Published from 1994-2006, IEE Proceedings - Vision, Image and Signal Processing contained significant and original contributions on computer vision, image processing and signal processing.

Full Aims & Scope