Showing papers in "Signal Processing in 1991"

TL;DR: A new concept, that of INdependent Components Analysis (INCA), more powerful than the classical Principal components Analysis (in decision tasks) emerges from this work.

TL;DR: It is shown that the HJ algorithm is actually searching common zeros of n functionals by pipelined stochastic iterations by using the gradient of a single C a functional contrary to what is sometimes understood.

TL;DR: This paper derives a number of quantitative rules for reducing the rank of signal models that are used in signal processing algorithms.

TL;DR: The stability analysis of the adaptive two-cell Herault-Jutten network for separation of sources from the observation of a linear mixture is presented.

TL;DR: In this paper, the authors investigated the application of a non-linear structure to the adaptive channel equalization of a bipolar signal passed through dispspersive channel in the presence of additive noise and showed that the optimal equalization solution under the classical architecture of making decisions symbol-by-symbol is an inherently nonlinear problem.

TL;DR: A unified statistical performance analysis using perturbation expansions is applied to subspace-based algorithms for direction-of-arrival (DOA) estimation in array signal processing using the MUSIC, Min-Norm, State-Space Realization, and ESPRIT algorithms.

TL;DR: Bounds on several component measures of the degree of nonstationarity for stochastic processes that exhibit cyclostationarity are derived and their utility in applications involving signal detection and estimation is established.

TL;DR: A versatile algorithm for computing dilations and erosions of digital binary pictures with structuring elements of arbitrary size and shape that turns out to be extremely fast whatever the utilized elements.

TL;DR: An eigenstructure based method for simultaneously estimating directions of arrival (DOA) and sensor locations is developed and offers an alternative to the procedure presented by Weiss and Friedlander (1990).

TL;DR: It is shown how signal processing algorithms combined with pattern recognition techniques allow extraction of information about spectral characteristics and type of modulation.

TL;DR: The feasibility of processing the Fourier transform (FT) phase of a speech signal to derive the smooth log magnitude spectrum corresponding to the vocal tract system is demonstrated and a technique to extract the vocal tracts component of the group delay function is proposed by using the spectral properties of the excitation signal.

TL;DR: The robustness of an L p normed solution when estimating the frequency of sinusoids from data contaminated by impulsive noise is demonstrated and insight is gained into the transient and steady behavior of the iterative algorithm.

TL;DR: A nonstochastic alternative to the stochastic process framework for conceptualizing, modeling and analyzing time-series encountered in communications, radar and telemetary systems is proposed and Wold's isomorphism is generalized to accomodate time- series with periodic structure and corresponding cycloergodic cyclostationary Stochastic processes.

TL;DR: This paper presents a technique for designing a notch filter with controlled null width to minimize the mean square error between the desired unity response and the response of the filter over a frequency band of interest subject to a controlled broad null.

TL;DR: To recover the system nonlinearity the Legendre orthogonal polynomials based procedure is proposed and the procedure consistency and the rate of convergence are established.

TL;DR: This paper focuses on the class of nonnegative quadratic functionals whose minimization amounts to 2-D L-generalized splines, and proposes a number of interpolation algorithms, based on various noncausal and semicausal SPDE image models.

TL;DR: Local phase information obtained by Gabor filtering may be used for texture discrimination and image segmentation purposes and the phase gradient and local demodulation methods can render useful boundary and region information if simple test images are considered.

TL;DR: This paper analyzes the mean-square error (MSE) in the DOA estimates obtained with the MUSIC algorithm under sensor gain and phase perturbations, using first-order perturbation analysis.

TL;DR: The Fast Least Squares algorithms based on the QR triangular decomposition of the input signal matrix and developed for the case of one-dimensional signals can be extended to handle the cases of multi-dimensional (MD) or multichannel signals.

TL;DR: Computer simulation results show that the proposed half-band FIR filter for pyramid construction yields a higher peak signal-to-noise ratio (PSNR) as well as better image quality, in comparison with other currently used filters of the same computational complexity.

TL;DR: This paper reformulates this hidden fractal model (HFM) problem in the scalar case as a higher order scalar or first order 2-vector homogeneous hidden Markov model ( HMM) problem, and can apply HMM signal processing techniques to obtain optimal estimates of the signals and signal model parameters, including transition probabilities and noise statistics.

TL;DR: This dissertation presents two adaptive algorithms for the detection of small changes/targets in a pair of images in a low signal to clutter plus noise ratio (SCNR) environment (of the order of $-$14.5 dB).

TL;DR: A detailed mathematical description of the basic physics and of the image formation process is given in the framework of the classical theory.

TL;DR: It is shown that the proposed algorithm for computing a singular value decomposition of a product of three matrices is numerically desirable in that all relevant residual elements will be numerically small.

TL;DR: Simulation results show the outstanding performances of the whole encoding scheme, especially its high data compression capability and good subjective image reconstruction.

TL;DR: An optimal deconvolution filter design approach is introduced for multi-channel systems under coloter noise and can be applied to both minimum-phase and nonminimum-phase systems.

TL;DR: The theoretical basis and short descriptions of some applications: the measurement of signal parameters, amplitude and frequency detection, data compression, rejection and filtering, malfunction diagnosis, identification and extrapolation are presented.

TL;DR: The spectral and implementation aspects of forward and backward predictors based on Newton-type extrapolation based on Compact formulae for calculating the predictor coefficients are derived and the potential of applying Newton- type predictors in reducing the required memory size of large look-up tables is presented.

TL;DR: An algorithm for multiscale description of binary digital regions that satisfies meaningful algebraic properties and converges to a final result in a bounded number of steps and allows an economical representation of shape in terms of structuring elements, and so it can be applied in binary image coding.

TL;DR: Algorithms for improving the quality of skeletons obtained from sequential thinning processes take into consideration the shape of the contours in the dynamic removal and placement of pixels in order to obtain skeletons that are more representative of the shapes of the original patterns.