Showing papers in "Signal Processing in 1993"

TL;DR: This method serves three purposes: it accurately locates boundaries between changed and unchanged areas, it brings to bear a regularizing effect on these boundaries in order to smooth them, and it eliminates small regions if the original data permits this.

TL;DR: This work discusses the general properties of the CWT and applies it, both analytically and graphically, to a number of simple geometrical objects: a line, a square, an angle, etc.

TL;DR: A direction finding technique which uses the outputs of a virtual array, computed from the real array using a linear interpolation procedure over a given sector, which was found to equal the performance of the MUSIC algorithm applied to the realarray.

TL;DR: This paper presents an extension of the family of orthogonal Battle/Lemarie spline wavelet transforms with emphasis on filter bank implementation, and considers the special cases of Orthogonal, B-spline, cardinal and dual wavelets.

TL;DR: A signal-dependent kernel that changes shape for each signal to offer improved time-frequency representation for a large class of signals is proposed and an efficient scheme based on Newton's algorithm for finding the optimal kernel is developed.

TL;DR: A comprehensive list of basic and recent references on spectral line analysis, which contains a myriad of techniques and analysis methods, many of them borrowed from other fields, such as time-series analysis, system identification, matrix algebra, multivariate statistical analysis, complexity theory and others.

TL;DR: This paper presents perception as a process of dynamically maintaining a model of the local external environment and proposes a set of principles for the ‘fusion’ of independent observations which permit perceptual fusion with qualitatively different forms of data.

TL;DR: Two canonical decompositions of mappings between complete lattices are presented, based on the mathematical morphology elementary mappings: erosions, anti-erosions, dilations and anti-dilations, by introducing the concept of morphological connection, that extends the notion of Galois connection.

TL;DR: The newly proposed signal enhancement algorithm can be successfully applied to the quantitative time-domain analysis of Nuclear Magnetic Resonance (NMR) data and reduces drastically the required computation time.

TL;DR: This paper assumes that the parameters structure the mean value vector in a multivariate normal distribution and the Fisher matrix is a Gramian constructed from the sensitivity vectors that characterize the first-order variation in the mean with respect to the parameters.

TL;DR: A transformation matrix is derived that makes it possible to theoretically attain the full-dimension Cramer-Rao bound also in the reduced space and the problem of estimating parameters of sinusoidal signals from noisy data is addressed by a direct application of the results derived herein.

TL;DR: It is proved that using higher-than-second-order cumulants, it is possible to estimate more angles-of-arrival (or harmonics) with fewer sensors and the problem of detecting the number of sources using output Cumulants only is addressed.

TL;DR: Modified versions of the corresponding algorithm are proposed and a theoretical formula for the asymptotic variance of the estimator is derived, which generalizes the spectral properties of ARCOS.

TL;DR: Two algorithms based on a new conditional entropy measure of a partitioned image have been formulated using the Poisson distribution for the gray level instead of the commonly used normal distribution and are found to produce good results.

TL;DR: A problem-independent control algorithm for the interpretation of sensor signals is presented which provides both data-driven and model-driven control structures which can easily be combined to perform any mixed strategy.

TL;DR: A computationally very efficient procedure for the estimation of time varying VAR model with time varying coefficients is developed by using the VAR representation with instantaneous response and the Kalman filter.

TL;DR: Some of the traditional algorithms, generally used in image restoration, as MAP, MPM or ICM, are shown to be very efficient for the deconvolution of Bernoulli-Gaussian processes.

TL;DR: First-order expressions for the mean square error (MSE) of the parameter estimates are derived for the deterministic and stochastic maximum likelihood methods and the weighted subspace fitting technique and the spatial noise correlation structures that lead to maximum performance loss are identified under different assumptions.

TL;DR: A class of multiscale stochastic processes which are modeled using dynamic representations evolving in scale based on the wavelet transform can be well-approximated, leading to new, highly parallel and scale-recursive estimation algorithms for multi-scale data fusion.

TL;DR: Simulation results show that the proposed algorithm not only has much higher detection rate than Wax's Minimum Description Length method, but also achieves the CR bound at a lower threshold SNR than that of the Modified Forward Backward Linear Prediction (MFBLP) method proposed by Tufts and Kumaresan.

TL;DR: It is shown analytically that if the aperture of a p -sensor linear array with arbitrary inter-sensor spacings is greater than or equal to ( p −1)λ/2, where λ is the wavelength of the signal of interest, then rank-one ambiguity exists.

TL;DR: By examining the various forms in which the Gabor equations can be expressed, it is discovered how the input, window, biorthogonal function, Gabor coefficients and Zak transforms map under periodization and sampling.

TL;DR: Using the superposition of a linear and a quadratic operator, noise smoothing is achieved without blurring the details of the picture in gray-level images of documents.

TL;DR: To cope with the problem of interference between the image's components, a systematic extension of the most commonly used 1-D (one-dimensional) smoothing techniques to 2-D WVD case is proposed.

TL;DR: An advanced document images analysis which involves a multi-layer description of a document and leads to a semantic analysis of its content for an adaptive coding orientation in order to optimize the archiving is described.

TL;DR: A supervised segmentation scheme in which a Bayesian approach incorporating a pyramid data structure is used, which leads to a significant simplification of the Spann and Wilson quadtree segmentation algorithm.

TL;DR: Numerical results show that the proposed techniques are very effective in the design of antenna pattern having an adjustable mainlobe width and minimum average sidelobe level.

TL;DR: It is shown that an optimal filter for noise removing in edge detection is the symmetric exponential filter of an infinite size (ISEF), which can be explained and unified by the cascade of exponential filters presented for multi-edge detection.

TL;DR: It is shown that any real weighted median is equivalent to an integer weighted median, and this result proves very useful if one realizes that optimal adaptive weighted medians are usually real-valued.

TL;DR: This short communication reproduces the analysis from Anarim and Istefanopulos and obtains an expression for the variance which is identical to the expression derived by Sakai, Stoica and Nehorai.