IEEE Transactions on Signal Processing

Issue 1 • Jan. 1992

Filter Results

Displaying Results 1 - 25 of 32
  • Corrections to 'The LMS algorithm with delayed coefficient adaptation'

    Publication Year: 1992, Page(s):230 - 232
    Cited by:  Papers (56)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (211 KB)

    The analysis in an earlier paper (see Trans. Acoust. Speech and Signal Processing, vol.37, no.9, p.1397-405, 1989) is improved by correcting an error in the derivation of the system equation. After the correction, the system equation is modified, and thus, so are the related analytical results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection and localization of multiple sources in noise with unknown covariance

    Publication Year: 1992, Page(s):245 - 249
    Cited by:  Papers (55)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (424 KB)

    The authors present a novel technique for the detection and localization of multiple sources in the presence of noise with unknown and arbitrary covariance. The technique is applicable to coherent and noncoherent signals and to arbitrary array geometry and is based on Rissanen's minimum description length (MDL) principle (1989) for model selection. Its computational load is comparable to that of a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Incomplete sampling series and the recovery of missing samples from oversampled band-limited signals

    Publication Year: 1992, Page(s):225 - 227
    Cited by:  Papers (32)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (224 KB)

    It is well known that a band-limited oversampled signal is completely determined even if an arbitrary finite number of samples is lost. It is shown that an alternative simple proof of this fact carries over to generalized sampling expansions. More precisely, it is shown that any finite number of missing samples can be recovered from the remaining ones, in the case of generalized Kramer sampling ex... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On two-dimensional maximum entropy spectral estimation

    Publication Year: 1992, Page(s):241 - 244
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (332 KB)

    A novel method of two-dimensional spectral estimation, which the authors introduced recently (1987) using the Radon transform and a one-dimensional autoregressive model (AR), led them to investigate the maximization of entropy subject to the correlation matching constraints in the Radon space. Instead of solving the 2D maximum entropy (ME) spectral estimation problem, the authors convert it into a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fast finite-state algorithm for vector quantizer design

    Publication Year: 1992, Page(s):221 - 225
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (440 KB)

    The Linde-Buzo-Gray (LBG) algorithm is usually used to design a codebook for encoding images in vector quantization. In each iteration of this algorithm, one must search the full codebook in order to assign the training vectors to their corresponding codewords. Therefore, the LBG algorithm needs a large computation effort to obtain a good codebook from the training set. The authors propose a finit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A VLSI architecture for real-time image coding using a vector quantization based algorithm

    Publication Year: 1992, Page(s):181 - 189
    Cited by:  Papers (20)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (884 KB)

    Digital image coding using vector quantization (VQ) based techniques provides low-bit rates and high quality coded images, at the expense of intensive computational demands. The computational requirement due to the encoding search process, had hindered application of VQ to real-time high-quality coding of color TV images. Reduction of the encoding search complexity through partitioning of a large ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A differential lossless image compression scheme

    Publication Year: 1992, Page(s):236 - 241
    Cited by:  Papers (16)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (928 KB)

    A low-complexity, lossless image compression algorithm which is suitable for real-time implementation is presented. The algorithm codes each pixel into a set of two symbols, a prefix and a suffix. The prefix is the number of most significant bits which are identical in a reference pixel, while the suffix is the remaining bits except for the left-most bit. Three methods, two fixed and one adaptive,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Digital differentiation of noisy data measured through a dynamic system

    Publication Year: 1992, Page(s):218 - 221
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (332 KB)

    The design of discrete time differentiating filters, in the presence of colored noise and nonneglectable transducer dynamics, is investigated. The signal and noise are described by autoregressive moving average (ARMA) models, possibly with poles on |z|=1. The mean square error (MSE) optimal filter, based on a discrete time approximation of the derivative operator, is given by a spectral f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two-dimensional polynomial interpolation from nonuniform samples

    Publication Year: 1992, Page(s):169 - 180
    Cited by:  Papers (17)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (868 KB)

    The authors derive a number of results on sufficient conditions under which the 2-D polynomial interpolation problem has a unique or nonunique solution. It is found that, if the sum of the degrees of the irreducible curves on which the interpolation points are chosen is small compared to the degree of the interpolating polynomial, then the problem becomes singular. Similarly, if there are too many... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Conditioning contexts for the arithmetic coding of bit planes

    Publication Year: 1992, Page(s):232 - 236
    Cited by:  Papers (14)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (852 KB)

    The arithmetic coding of the bit planes of an image represented either in the conventional weighted binary form or by the Gray code, is investigated. Two-dimensional contexts based on the pixels from the current bit plane and three-dimensional contexts on pixels from both the current and previous bit planes are studied. Results indicate that for binary bit planes, a three-dimensional template resu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A unified approach to three eigendecomposition methods for frequency estimation

    Publication Year: 1992, Page(s):213 - 218
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    The authors present a unified approach to three eigendecomposition-based methods for frequency estimation in the presence of noise. These are the Tufts-Kumaresan (TK) method, the minimum-norm (MN) method, and the total least squares (TLS) method. It is shown that: (1) the MN method is a modified version of the TK method; (2) the TLS method is a generalization of the MN method; (3) the TLS solution... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On updating signal subspaces

    Publication Year: 1992, Page(s):96 - 105
    Cited by:  Papers (65)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (772 KB)

    The authors develop an algorithm for adaptively estimating the noise subspace of a data matrix, as is required in signal processing applications employing the `signal subspace' approach. The noise subspace is estimated using a rank-revealing QR factorization instead of the more expensive singular value or eigenvalue decompositions. Using incremental condition estimation to monitor the smallest sin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bias-remedy least mean square equation error algorithm for IIR parameter recursive estimation

    Publication Year: 1992, Page(s):62 - 69
    Cited by:  Papers (35)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (584 KB)

    In the area of infinite impulse response (IIR) system identification and adaptive filtering the equation error algorithms used for recursive estimation of the plant parameters are well known for their good convergence properties. However, these algorithms give biased parameter estimates in the presence of measurement noise. A new algorithm is proposed on the basis of the least mean square equation... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Root signals of rank order processors

    Publication Year: 1992, Page(s):32 - 43
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1008 KB)

    A rank order processor (ROP) is a signal processor that operates purely by making rank determination on input values, and includes as special cases `median filters' and `rank order filters'. It is shown how the methods of automata theory can be used to show the existence of root signal (i.e., fixed point) sets of input sequences, and to determine them for specific ROPs, in either algebraic or grap... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Passive ranging in multipath dominant environments. I. Known multipath parameters

    Publication Year: 1992, Page(s):1 - 12
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (828 KB)

    Passive ranging accuracy using arrays deteriorates at long ranges because of the vanishing wavefront curvature observable by an array. The idea of including a priori knowledge of propagation conditions in ranging procedures for the purpose of improving the range estimate has received considerable attention in recent years. The interest is based on an observation that a large propagation delay meas... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image restoration by convex projections using adaptive constraints and the L1 norm

    Publication Year: 1992, Page(s):159 - 168
    Cited by:  Papers (25)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1140 KB)

    A new projection method based on the row action projection (RAP) algorithm for image restoration is presented. The new implementation is computationally attractive and facilitates local adaption of projection operators. The local mean and the least L1 norm set of solutions are used as constraints. Computer simulations illustrate the new methods to be very competitive in restori... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Asymptotic performance of a distributed detection system in correlated Gaussian noise

    Publication Year: 1992, Page(s):211 - 213
    Cited by:  Papers (33)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (220 KB)

    The authors consider the detection of a constant signal in noise with a large set of geographically dispersed sensors. The noise at the sensors is correlated Gaussian. Two correlation models are considered: one where the correlation coefficient between any two sensors decreases geometrically as the sensor separation increases, and one in which the correlation coefficient between any two sensors is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Floating point arithmetic and digital filters

    Publication Year: 1992, Page(s):85 - 95
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (832 KB)

    The roundoff noise properties of floating point digital filters are examined. To make the analysis tractable, a high level model to deal with the errors in the inner product operation is developed. This model establishes a broad connection between coefficient sensitivity and roundoff noise. Along with the model, an efficient procedure to keep track of the addition scheme used in the inner product,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computation of an odd-length DCT from a real-valued DFT of the same length

    Publication Year: 1992, Page(s):54 - 61
    Cited by:  Papers (34)  |  Patents (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    The discrete cosine transform (DCT) is often computed from a discrete Fourier transform (DFT) of twice or four times the DCT length. DCT algorithms based on identical-length DFT algorithms generally require additional arithmetic operations to shift the phase of the DCT coefficients. It is shown that a DCT of odd length can be computed by an identical-length DFT algorithm, by simply permuting the i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stability of digital filters implemented with two's complement truncation quantization

    Publication Year: 1992, Page(s):24 - 31
    Cited by:  Papers (26)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (528 KB)

    The stability of digital filters implemented with two's complement truncation quantization is investigated. Both the direct-form and normal-form realizations are considered and regions in the parameter plane are obtained where the filters are globally asymptotically stable. Regions within the stability triangle of a direct-form digital filter are also studied where limit cycles of period one and t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiphase systolic algorithms for spectral decomposition

    Publication Year: 1992, Page(s):190 - 201
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (948 KB)

    The authors propose two multiphase systolic algorithms to solve the spectral decomposition problem based on the QR algorithm. The spectral decomposition is one of the most computationally intensive modern signal processing operations. While the QR algorithm is well known to be an effective method to solve the eigenvalue problem, there is still no single systolic array architectur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Numerical performances of autoregressive spectrum estimators based on three-term recurrences

    Publication Year: 1992, Page(s):249 - 252
    Cited by:  Papers (1)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (316 KB)

    The numerical performance of two fast algorithms for estimating the power spectral density of an autoregressive process is studied. The algorithms perform similarly to the Burg algorithm, but require only two-thirds as many multiplications as the most efficient implementation of the Burg algorithm. This allows the high resolution associated with the Burg algorithm to be obtained using many fewer c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improved polarity coincidence spectral-centroid estimator

    Publication Year: 1992, Page(s):227 - 230
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (280 KB)

    An extension of the polarity coincidence (PC) method for estimating the center frequency of a power spectral density (PSD) is proposed. By applying Price's theorem, the variance of this new estimator for Gaussian processes is evaluated. Its performance is compared and related to that of the averaged output of an ideal tuned FM receiver View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fast new algorithm for training feedforward neural networks

    Publication Year: 1992, Page(s):202 - 210
    Cited by:  Papers (133)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1060 KB)

    A fast algorithm is presented for training multilayer perceptrons as an alternative to the backpropagation algorithm. The number of iterations required by the new algorithm to converge is less than 20% of what is required by the backpropagation algorithm. Also, it is less affected by the choice of initial weights and setup parameters. The algorithm uses a modified form of the backpropagation algor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Time delay estimation using the cross bispectrum

    Publication Year: 1992, Page(s):106 - 113
    Cited by:  Papers (31)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (620 KB)

    The cross bispectrum phase can be effectively used to estimate the time required for a nonGaussian signal to propagate between a pair of spatially separated sensors in the presence of highly correlated Gaussian noise. The authors present a consistent estimator of the phase of the cross bispectrum, derive the exact distribution of the phase of a complex Gaussian sample bispectrum, and show that in ... View full abstract»

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

Aims & Scope

IEEE Transactions on Signal Processing covers novel theory, algorithms, performance analyses and applications of techniques for the processing, understanding, learning, retrieval, mining, and extraction of information from signals

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
Sergios Theodoridis
University of Athens