检索结果-内蒙古大学图书馆

IEEE/SP Workshop on statistical Signal processing (SSP)

作者： J.M. Siskind I. Pollak P. Harper Bouman Purdue University USA

We describe a class of multiscale stochastic processes based on stochastic context-free grammars and called spatial random trees (SRTs) which can be effectively used for modeling multidimensional signals. In addition to modeling images which are sampled on a regular rectangular grid, we generalize this methodology to images defined on arbitrary graph structures. We develop likelihood calculation, MAP estimation, and EM-based parameter estimation algorithms for SRTs. To illustrate these methods, we apply them to classification of natural images using region graphs extracted by a recursive bipartitioning segmentation algorithm.

关键词： stochastic processes Parameter estimation Tree graphs Context modeling Multidimensional signal processing Signal processing image segmentation

来源：评论

学校读者我要写书评

暂无评论

Extended quality identifiers for radar measurements

Extended quality identifiers for radar measurements

引用

International Conference on Antenna Theory and Techniques

作者： A.V. Ksendzuk Kharkov National Aerospace University KhAI Ukraine

Synthetic aperture radar and ordinary radar systems must be optimized with respect to some quality criteria. A commonly used optimization gives minimum mean-square variance error. However, this optimization cannot take into account all characteristics of the radar image, such as speckle. This leads to a number of non-optimal secondary processing algorithms (nonlinear filtering, statistical estimation, etc.). The paper presents common quality criteria applicable to space and space-time processing. Radar image formation errors are separated into three kinds: dynamic, fluctuation and noise errors. Dynamic errors are caused by smoothing the radar space ambiguity function. One realisation of the stochastic process observed during the finite time interval leads to inconsistent estimation, which is called fluctuation error (speckle noise). Noise error is caused by additional noise present in the input. The paper proposes statistical criteria applicable to optimizing the processing algorithms in radar systems.

关键词： Radar measurements Radar imaging Fluctuations Parameter estimation Signal processing Speckle Synthetic aperture radar Aerodynamics Smoothing methods Estimation error

来源：评论

学校读者我要写书评

暂无评论

Mathematical methods in imaging

引用

IEEE SIGNAL processing MAGAZINE 2002年第5期19卷 13-14页

作者： Hero, AO Krim, H Univ Michigan Ann Arbor MI 48109 USA N Carolina State Univ Raleigh NC 27695 USA

Not Available

关键词： Fractals stochastic processes Signal processing algorithms image analysis statistical analysis image restoration History Africa Psychology Fingerprint recognition

来源：评论

学校读者我要写书评

暂无评论

Multiresolution Markov models for signal and image processing

引用

PROCEEDINGS OF THE IEEE 2002年第8期90卷 1396-1458页

作者： Willsky, AS MIT Dept Elect Engn & Comp Sci Lab Informat & Devis Syst Cambridge MA 02139 USA

This paper reviews a significant component of the rich field of statistical multiresolution (MR) modeling and processing. These MR methods have found application and permeated the literature of a widely scattered set of disciplines, and one of our principal objectives is to present a single, coherent picture of this framework. A second goal is to describe how this topic fits into the even larger field of MR methods and concepts-in particular, making ties to topics such as wavelets and multigrid methods. A third goal is to provide several alternate viewpoints for this body of work, as the methods and concepts we describe intersect with a number of other fields. The principle focus of our presentation is the class of MR Markov processes defined on pyramidally organized trees. The attractiveness of these models stems from both the very efficient algorithms they admit and their expressive power and broad applicability. We show how a variety of methods and models relate to this framework including models for self-similar and 1/f processes. We also illustrate how these methods have been used in practice. We discuss the construction of MR models on trees and show how questions that arise in this context make contact with wavelets, state space modeling of time series, system and parameter identification, and hidden Markov models. We also discuss the limitations of tree-based models and algorithms and the artifacts that they can introduce. We describe when these are of concern and ways in which they can be overcome. This leads to a discussion of MR models on more general graphs and ties to well-known and emerging methods for inference on graphical models.

关键词： autoregressive processes Bayesian networks data assimilation data fusion estimation fractals geophysical signal processing graphical models hidden Markov models image enhancement image processing image segmentation inverse problems Kalman filtering machine vision mapping Markov random fields maximum entropy methods multiresolution (MR) methods quadtrees signal processing sparse matrices state space methods stochastic realization trees wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

statistical properties of x-ray CT and MRI: from imaging physics to image statistics

Statistical properties of x-ray CT and MRI: from imaging phy...

引用

Medical Imaging 2002 Conference

作者： Lei, TH Udupa, JK Univ Penn Dept Radiol Med Image Proc Grp Philadelphia PA 19104 USA

ISBN: (纸本)0819444278

Physical and mathematical procedures of x-ray CT and MRI have been extensively studied during the past three decades. The statistical methods of image reconstruction, processing and analysis of x-ray CT and MRI have been widely used in the various fields. However, the lack of a complete description and a rigorous proof of their statistical properties become a common concern. This study attempts to fill this gap and discusses a framework for studing the statistical aspects of x-ray CT and MRI. A statistical investigation has been conducted into x-ray CT and MRI, from their physical imaging procedure, through mathematical image reconstruction, to the resulting images. A set of intrinsic statistical properties have been derived and proved. They include Gaussianity, independence, correlation, stationarity, ergodicity, autocorrelation function, spectral density function, and information content of x-ray CT and MR images. These statistical properties establish the relationship between the parameters in imaging systems, image reconstruction algorithms, and the statistical behavior of x-ray CT and MR images. They can be directly applied to image reconstruction, processing, and analysis, and also can be used as a theoretical basis for establishing stochastic image models. The method used in this study can be extended to more advanced imaging systems and image reconstruction algorithms, as well as to other nondiffraction CT modalities, with some modifications.

关键词： imaging physics statistical property correlation stochastic model

来源：评论

学校读者我要写书评

暂无评论

Variational methods for Multimodal image Matching

Variational Methods for Multimodal Image Matching

引用

作者： Gerardo Hermosillo Valadez Grenoble Alpes University

学位级别：博士

During the past few years, the use of the theory of partial differential equations has provided a solid formal approach to image processing and analysis research, and has yielded provably well-posed algorithms within a set of clearly defined hypotheses. These algorithms are the state-of-the-art in a large number of application fields such as image de-noising, segmentation and matching. At the same time, the combination of stochastic and variational approaches has led to powerful algorithms which may also be described in terms of partial differential equations. This is the approach fol- lowed in the present work, which studies the problem of dense matching between two images using statistical dissimilarity criteria. Two classes of algorithms are consid- ered, corresponding to these criteria being calculated globally for the entire image, or locally within corresponding regions. In each case, three dissimilarity criteria are stud- ied, defined as the opposite of the following similarity measures: mutual information (well adapted to a general statistical dependence between the grey-level intensities), correlation ratio (adapted to a functional dependence), and cross correlation (adapted to an affine dependence). The minimization of the sum of the dissimilarity term and a regularization term defines, through the associated Euler-Lagrange equations, a set of coupled functional evolution equations. Particular emphasis is put in establishing the conditions under which these evolution equations are well posed, i. e. they have a unique solution. It is shown that the proposed algorithms satisfy these conditions for two classes of linear regularization terms, including one which encourages discontinu- ities of the solution at the contours of the reference image. The discretization and the numerical implementation of the matching algorithms is discussed in detail and their performance is illustrated through several real and synthetic examples, both with 2D and 3D images. As the

关键词：

来源：评论

学校读者我要写书评

暂无评论

Updating mixture of principal components for error concealment

Updating mixture of principal components for error concealme...

引用

IEEE International Conference on image processing

作者： Trista Pei-chun Tsuhan Chen Dept. of Electr. & Comput. Eng. Carnegie Mellon Univ. Pittsburgh PA USA Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA U.S.A.

ISBN: (纸本)0780376226

We present a new statistical modeling technique called "updating mixture of principal components" (UMPC). UMPC specifically captures the non-stationary as well as the multi-modal characteristics of the data. Real-world data such as video data typically have these two characteristics. The video content changes over time and has a multi-modal probability distribution. We apply UMPC to perform error concealment for video data transmitted over networks with losses, and show that UMPC outperforms conventional error concealment methods.

关键词： Probability distribution Propagation losses image reconstruction Error correction Computer errors Iterative decoding Video sequences statistical distributions stochastic processes

来源：评论

学校读者我要写书评

暂无评论

Experiment design-based regularization technique for scattering inverse problem solution in radar imaging

Experiment design-based regularization technique for scatter...

引用

Antennas and Propagation Society International Symposium

作者： Yu. Shkvarko L. Leyva-Montiel CINVESTAV del IPN Unidad Guadalajara Guadalajara Mexico

ISBN: (纸本)0780373308

The crucial theoretical aspects in solving scattering inverse problems, as required for radar sensing and image formation, are related to the development of system-oriented statistical signal processing techniques, exploiting in some optimal way the available model-level and system-level "degrees of freedom". Control of these degrees of freedom is the hope for solving many existing algorithm design and system-level problems that cause the ill-posed nature of the radar image formation inverse problems. We address a new approach to radar imaging (RI) problems, stated and treated as ill-posed problems of restoring the extended object power scattering function by processing the data signals distorted in the stochastic measurement channel. By exploiting the idea of combining the experiment design and descriptive regularization theory methods (see Falkovich, S.E. et al., Radio i Sviaz, 1989; Harmanci, K. et al., IEEE Trans. Sig. Proc., vol.48, no.1, p.1-13, 2000; Kravchenko, V.F. et al., J. Commun. Technology and Electronics, vol.45, no.8, p.872-5, 2000) for the scattering inverse problems solution, we propose a fused experiment-design-regularization (EDR) technique for high-resolution radar image formation. With this technique, we derive a family of EDR imaging algorithms and illustrate their efficiency with simulation results.

关键词： Radar scattering Inverse problems Radar imaging Signal processing algorithms Radar signal processing Radar theory Control systems Algorithm design and analysis image restoration Power system restoration

来源：评论

学校读者我要写书评

暂无评论

Higher-order statistical properties arising from the non-stationarity of natural signals

Higher-order statistical properties arising from the non-sta...

引用

14th Annual Neural Information processing Systems Conference (NIPS)

作者： Parra, L Spence, C Sajda, P Sarnoff Corp Adapt Signal & Image Proc Princeton NJ 08540 USA

ISBN: (纸本)0262122413

We present evidence that several higher-order statistical properties of natural images and signals can be explained by a stochastic model which simply varies scale of an otherwise stationary Gaussian process. We discuss two interesting consequences. The first is that a variety of natural signals can be related through a common model of spherically invariant random processes, which have the attractive property that the Joint densities can be constructed from the one dimensional marginal. The second is that in some cases the non-stationarity assumption and only second order methods can be explicitly exploited to find a linear basis that is equivalent to independent components obtained with higher-order methods. This is demonstrated on spectro-temporal components of speech.

关键词： stochastic models

来源：评论

学校读者我要写书评

暂无评论

A robust algorithm for fusing noisy depth estimates using stochastic approximation

A robust algorithm for fusing noisy depth estimates using st...

引用

IEEE International Conference on Acoustics, Speech, and Signal processing

作者： Chowdhury, AKR Chellappa, R Center for Automation Research Dept. of Elec. and Comp. Engineering University of Maryland College Park MD 20742 United States

ISBN: (纸本)0780370414

The problem of structure from motion (SFM) is to extract the three-dimensional model of a moving scene from a sequence of images. Most of the algorithms which work by fusing the two-frame depth estimates (observations) assume an underlying statistical model for the observations and do not evaluate the quality of the individual observations. However, in real scenarios, it is often difficult to justify the statistical assumptions. Also, outliers are present in any observation sequence and need to be identified and removed from the fusion algorithm. In this paper, we present a recursive fusion algorithm using Robbins-Monro stochastic approximation (RMSA) which takes care of both these problems to provide an estimate of the real depth of the scene point. The estimate converges to the true value asymptotically. We also propose a method to evaluate the importance of the successive observations by computing the Fisher information (FI) recursively. Though we apply our algorithm in the SFM problem by modeling of human face, it can be easily adopted to other data fusion applications.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：