Impulse noise

About: Impulse noise is a research topic. Over the lifetime, 4816 publications have been published within this topic receiving 63970 citations.

An innovative parameter estimation for fractional order systems with impulse noise

Abstract: This paper investigates the problem of parameter estimation for fractional order linear systems when the output signal is polluted by impulse noise. The conventional least square error objective function is replaced by a new approximate least absolute error (ALAE) function to restrain the influence of impulse noise. Then a novel parameter estimation approach is designed based on the stochastic gradient method, the fractional order parameter update law and the ALAE criterion, which improves estimation accuracy and enhances robustness at the same time. It is shown that the adoption of the fractional order parameter update law ensures larger selection range of update order and smoother convergence of the algorithm. The effectiveness and superiority of the proposed method are verified by strict mathematical analysis and detailed numerical examples.

Nearly Optimal Detection of Signals in Non-Gaussian Noise

Abstract: : This dissertation addresses the problem of finding nearly optimal detector structures for non-Gaussian noise environments. It is assumed that the noise statistics are unknown except for a very loose characterization. Under this condition, the goal is to study adaptive detector structures that are simple, yet capable of high levels of performance. Attention is focused on the discrete-time locally optimal detector for a constant signal in independent, identically distributed noise. A definition for non-Gaussian noise is given, several common univariate density models are exhibited, and some physical non- Gaussian noise data is discussed. Two approaches in designing adaptive detector nonlinearities are presented, where it is assumed that the noise statistics are approximately stationary. Both proposals utilized simple measurements of the noise behavior to adapt the detector, and in several examples the adaptive detectors are shown capable of attaining nearly optimal performance levels. A simulation is presented demonstrating their successful application.

Patch group based bayesian learning for blind image denoising

Abstract: Most existing image denoising methods assume to know the noise distributions, e.g., Gaussian noise, impulse noise, etc. However, in practice the noise distribution is usually unknown and is more complex, making image denoising still a challenging problem. In this paper, we propose a novel blind image denoising method under the Bayesian learning framework, which automatically performs noise inference and reconstructs the latent clean image. By utilizing the patch group (PG) based image nonlocal self-similarity prior, we model the PG variations as Mixture of Gaussians, whose parameters, including the number of components, are automatically inferred by variational Bayesian method. We then employ nonparametric Bayesian dictionary learning to extract the latent clean structures from the PG variations. The dictionaries and coefficients are automatically inferred by Gibbs sampling. The proposed method is evaluated on images with Gaussian noise, images with mixed Gaussian and impulse noise, and real noisy photographed images, in comparison with state-of-the-art denoising methods. Experimental results show that our proposed method performs consistently well on all types of noisy images in terms of both quantitative measure and visual quality, while those competing methods can only work well on the specific type of noisy images they are designed for and perform poorly on other types of noisy images. The proposed method provides a good solution to blind image denoising.