检索结果-内蒙古大学图书馆

Solving Quadratic systems With Full-Rank Matrices Using Sparse or Generative Priors

IEEE TRANSACTIONS ON SIGNAL processing 2025年 73卷 477-492页

作者： Chen, Junren Ng, Michael K. Liu, Zhaoqiang Univ Hong Kong Dept Math Hong Kong 852 Peoples R China Hong Kong Baptist Univ Dept Math Hong Kong 852 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China

The problem of recovering a signal x is an element of R-n from a quadratic system{yi=x(T)A(ix), i=1,...,m} with full-rank matrices A(i) frequently arises in applications such a sun assigned distance geometry and sub-wavelength imaging. With i.i.d. standard Gaussian matrices A(i) , this paper addresses the high-dimensional case where m << n by incorporating prior knowledge of x. First, we consider a k-sparse x and introduce the thresholded Wirtinger flow (TWF) algorithm that does not require the sparsity level k. TWF comprises two steps: the spectral initialization that identifies a point sufficiently closetox (up to a sign flip) when m=O(k(2)logn),and the thresholded gradient descent which, when provided a good initialization, produces a sequence linearly converging to x with m=O(k log n) measurements. Second, we explore the generative prior, assuming that x lies in the range of an L-Lipschitz continuous generative model with k-dimensional inputs in an l(2)-ball of radius r. With an estimate correlated with the signal, we develop the projected gradient descent (PGD)algorithm that also comprises two steps: the projected power method that provides an initial vector with O(root k log(L)/m) l(2)-error given m=O( k log(Lnr))measurements, and the projected gradient descent that refines the l(2)-error to O(delta) at a geometric rate when m=O(k log Lrn/delta(2)). Experimental results corroborate our theoretical findings and show that: (i)our approach for the sparse case notably outperforms the existing provable algorithm sparse power factorization;(ii) leveraging the generative prior allows for precise image recovery in the MNIST dataset from a small number of quadratic measurements.

关键词： Sparse matrices Complexity theory Signal processing algorithms Vectors Phase measurement Compressed sensing Standards Particle measurements image segmentation image reconstruction Generative prior projected gradient descent projected power method quadratic system sparse prior wirtinger flow

来源：评论

学校读者我要写书评

暂无评论

Fuzzy systems and Data Mining ix - Proceedings of FSDM 2023

Fuzzy Systems and Data Mining IX - Proceedings of FSDM 2023

引用

9th International Conference on Fuzzy systems and Data Mining, FSDM 2023

ISBN: (纸本)9781643684703

The proceedings contain 110 papers. The topics discussed include: advanced machine learning structures over big data repositories: definitions, models, properties, algorithms;eye tracking data mining based on fuzzy sets of fixations;towards a universal understanding of color harmony: fuzzy approach;the role of data stream mining in improving self-medication practices in the Syrian Arab Republic;an end-to-end solution for net promoter score estimation and explanation from social media using natural language processing;robust convolutional neural network for image classification with gaussian noise;development of a fuzzy approach for consistency determination of ATC students’ opinions during aircraft flight norms violation hazard identification;on the wavelet convolution neural networks for ultra-sound based breast cancer detection;enhanced multi-target tracking with combination of position, power and ambiguous doppler measurements;and wind loads on structures: a finite element-based computational fluid dynamics analysis in evaluating the wind tunnel effects on low-rise structures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An end-to-end deep convolutional neural network for image restoration of sparse aperture imaging system in geostationary orbit 9

An end-to-end deep convolutional neural network for image re...

引用

Conference on Optoelectronic Imaging and Multimedia Technology ix

作者： Zhao, Wenxiu Zhang, Xiaofang Wang, Jing Gu, Yun Beijing Inst Technol Sch Opt & Photon Beijing Peoples R China

ISBN: (纸本)9781510657014;9781510657007

The development of large-aperture telescopes employing monolithic mirrors has been greatly limited by technical constraints and the difficulty of processing and manufacturing. The sparse aperture imaging system employing multiple small-sub apertures arranged and combined onto a co-phasing surface can achieve the equivalent resolution to the fully-filled aperture system, which brings new research ideas for astronomical observation and ground survey. However, the sparsity of apertures will result in blurred imaging. In this paper, we focus on the high-resolution imaging from the geostationary orbit and propose a restoration method for blurred images obtained by the sparse aperture system with a 12-sub-aperture annular-like structure. A SASDeblurNet, containing U-shaped structures and skip connections, is proposed to rapidly restore blurred images end-to-end. MAE, MSE, DSSIM, Charbonnier, and edge loss functions are attempted to train a small amount of data sets in anticipation of better imaging results. The simulation results show that the image restored by the proposed method improves the PSNR by an average of 11 dB and the SSIM of the restoration image improves from 0.77 to 0.94, achieving a high resolution comparable to that of a full-aperture optical system. Compared with traditional non-blind deconvolution algorithms, SASDeblurNet can effectively remove the effect of artifacts. Our work shows that the proposed method has good real-time performance, generalization ability, and noise immunity, which can provide the corresponding data support for on-orbit and real-time observation of sparse aperture imaging systems.

关键词： image restoration sparse aperture imaging system deep learning U-net

来源：评论

学校读者我要写书评

暂无评论

Conditional GAN-based deep network for seamless large-FOV imaging by camera array 9

Conditional GAN-based deep network for seamless large-FOV im...

引用

Conference on Optoelectronic Imaging and Multimedia Technology ix

作者： Zhang, Weihang Li, Lianglong Suo, Jinli Dai, Qionghai Tsinghua Univ Dept Automat Beijing 100084 Peoples R China Tsinghua Univ Inst Brain & Cognit Sci Beijing 100084 Peoples R China

ISBN: (纸本)9781510657014;9781510657007

Due to limited spatial bandwidth, one has to compromise between large field of view and high spatial resolution in both photography and microscopy. This dilemma largely hampers revealing fine details and global structures of the target scene simultaneously. Recently, a mainstream method is formed by utilizing multiple sensors for synchronous acquisition across different sub-FOVs with high resolution and stitching the patches according to the spatial position of the cameras. Various inpainting algorithms have been proposed to eliminate the intensity discontinuities, but conventional optimization methods are prone to misalignment, seaming artifacts or long processing time, and thus unable to achieve dynamic gap elimination. By taking advantage of generative adversarial networks (GANs) on image generation and padding, we propose a conditional GAN-based deep neural network for seamless gap inpainting. Specifically, a short series of displaced images are acquired to characterize the system configuration, under which we generate patch pairs with and without gap for deep network training. After supervised learning, we can achieve seamless inpainting in gap regions. To validate the proposed approach, we apply our approach on real data captured by large-scale imaging systems and demonstrate that the missing information at gaps can be retrieved successfully. We believe the proposed method holds potential for all-round observation in various fields including urban surveillance and systems biology.

关键词： image inpainting camera array large-scale imaging generative adversarial network gap elimination

来源：评论

学校读者我要写书评

暂无评论

Building surface damage recognition based on synthetic data

Building surface damage recognition based on synthetic data

引用

Information Technology and Nanotechnology (ITNT), International Conference on

作者： L.A. Zherdeva E. Yu. Minaev N.A. Firsov Samara National Research University Samara Russia Image Processing Systems Institute Samara Russia

To detect surface damage to buildings, it is necessary to involve workers who are at risk of industrial injuries when inspecting hard-to-reach areas of industrial premises. Attraction of special means, such as aerial platforms, safety systems, etc. increase the financial costs with this approach. The use of unmanned aerial vehicles, coupled with neural network algorithms, can simplify this procedure. Due to the inaccessibility, the problem of obtaining training data for neural networks arises, which can be solved by synthesizing them in a virtual environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On-the-fly Data Pipeline for image processing enabling Real-time Persistence Correction 9

On-the-fly Data Pipeline for Image Processing enabling Real-...

引用

Conference on X-Ray, Optical, and Infrared Detectors for Astronomy ix as part of SPIE Astronomical Telescopes + Instrumentation Conference

作者： Mandla, Christopher Hameed, Muhammad Subhan Aracic, Viseslav Ott, Sabine Plattner, Markus Herkersdorf, Andreas Wild, Thomas Max Planck Inst Extraterr Phys D-85748 Garching Germany Tech Univ Munich Dept Integrated Syst Arcisstr 21 D-80333 Munich Germany

ISBN: (纸本)9781510636965

In this paper, we present our concept of an on-the-fly image processing pipeline for ground-based telescopes. Our focus lies on the correction of undesired but unavoidable detector effects like persistence. State of the art systems like ESO's NGC perform operation of detectors and acquisition of science data. Instrument operators monitor the science data stream during measurement. Detector issues like persistence worsen the image quality and impair the inspection tasks. To overcome these difficulties, we develop the real-time data processing system EIDAS (Enhanced Infrared Detector Acquisition System) as an add-on to the NGC. Therewith, detector effects in the raw image stream are corrected on-the-fly and astronomical objects are visualized more clearly for direct inspections. EIDAS accompanies CPU, FPGA and GPU as well as algorithms optimized for this hardware architecture. The system is designed generically, matching various types of detectors and their respective science data output.

关键词： Data Pipeline Data processing Infrared Detectors Real-time FPGA GPU

来源：评论

学校读者我要写书评

暂无评论

Simulating biogeo-optical dynamics in the bottom boundary layer: Northern Gulf of Mexico test case 9

Simulating biogeo-optical dynamics in the bottom boundary la...

引用

Conference on Ocean Sensing and Monitoring ix

作者： Jollif, Jason K. Ladner, Sherwin Smith, Travis Penko, Allison Jarosz, Ewa Lovitt, Todd Naval Res Lab Stennis Space Ctr MS 39529 USA Vencore 11091 Sunset Hills Rd Reston VA 20190 USA

ISBN: (纸本)9781510608733;9781510608740

Interdisciplinary coastal observations over a two-week period in the northern Gulf of Mexico reveal a complex and dynamic bottom boundary layer (BBL) that is characterized by both biological and suspended sediment (biogeo-) optical signals. Much of the BBL optical variance is concealed from remote sensing by the opacity of the nearly omnipresent surface river plume, however, the BBL physical dynamics and resulting optical excitation are indeed responding to surface wind stress forcing and surface gravity wave-induced turbulence. Here we present a series of numerical modeling efforts and approaches aimed towards resolving and simulating these observed biogeo- physical and -optical processes. First, we examine results from the Tactical Ocean Data System (TODS), which combines daily satellite imagery with numerical circulation model results to render a three-dimensional estimate of the optical field and then execute a reduced-order complexity advection-diffusion-reaction model to render hourly forecasts. Whereas the TODS system has the advantage of effectively assimilating both glider data and satellite images, the 3D generation algorithms still have difficulty in the northern Gulf's complex 3-layered system (surface plume, geostrophic interior, BBL). Second, we present results from the Coupled Ocean-Atmosphere Prediction (COAMPS) system that has been modified to include interactive surface-gravity wave simulations. Results from this complex numerical modeling system suggest that Stokes drift current (SDC) has a potentially major role in determining the physical and kinematic characteristics of the BBL, and will substantially impact model-based estimates of sediment resuspension and transport.

关键词： Ocean optics 3D modeling Coastal modeling Data modeling 3D image processing Complex systems Earth observing sensors Numerical modeling Satellite imaging Satellites Biomedical optics Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Proceedings of SPIE-IS and T Electronic Imaging - image processing: algorithms and systems ix

Proceedings of SPIE-IS and T Electronic Imaging - Image Proc...

引用

image processing: algorithms and systems ix

ISBN: (纸本)9780819484079

The proceedings contain 41 papers. The topics discussed include: detecting photographic and computer generated composites;imaging using synchrotron radiation for forensic science;PSO-based methods for medical image registration and change assessment of pigmented skin;descreening using segmentation-based adaptive filtering;a new DCT-based algorithm for numerical reconstruction of electronically recorded holograms;error minimizing algorithms for nearest neighbor classifiers;and spatially adaptive alpha-rooting in BM3D sharpening.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Collaborative Annotation for Reliable Natural Language processing 1

引用

丛书名： Focus,,Focus series (London, England)

2016年

作者： Fort Karën

ISBN: (数字)9781119307648

ISBN: (纸本)9781848219045

This book presents a unique opportunity for constructing a consistent image of collaborative manual annotation for Natural Language processing (NLP). NLP has witnessed two major evolutions in the past 25 years: firstly, the extraordinary success of machine learning, which is now, for better or for worse, overwhelmingly dominant in the field, and secondly, the multiplication of evaluation campaigns or shared tasks. Both involve manually annotated corpora, for the training and evaluation of the systems. These corpora have progressively become the hidden pillars of our domain, providing food for our hungry machine learning algorithms and reference for evaluation. Annotation is now the place where linguistics hides in NLP. However, manual annotation has largely been ignored for some time, and it has taken a while even for annotation guidelines to be recognized as essential. Although some efforts have been made lately to address some of the issues presented by manual annotation, there has still been little research done on the subject. This book aims to provide some useful insights into the subject. Manual corpus annotation is now at the heart of NLP, and is still largely unexplored. There is a need for manual annotation engineering (in the sense of a precisely formalized process), and this book aims to provide a first step towards a holistic methodology, with a global view on annotation.

关键词： acronyms xi introduction list ix annotation process weight context tasks annotation prototypes annotation challenges new metrics crowdsourcing recent phenomenon nonexperts crowd

来源：评论

学校读者我要写书评

暂无评论

An Approach to Select the Appropriate image Fusion Algorithm for Night Vision systems 9

An Approach to Select the Appropriate Image Fusion Algorithm...

引用

Conference on Electro-Optical Remote Sensing, Photonic Technologies, and Applications ix

作者： Schwan, Gabriele Scherer-Negenborn, Norbert Fraunhofer IOSB Karlsruhe Germany

ISBN: (纸本)9781628418590

For many years image fusion has been an important subject in the image processing community. The purpose of image fusion is taking over the relevant information from two or several images to construct one result image. In the past many fusion algorithms were developed and published. Some attempts were made to assess the results from several fusion algorithms automatically with the objective of gaining the best suited output for human observers. But it was shown, that such objective machine-assessment does not always correlate with the observer's subjective perception. In this paper a novel approach is presented, which selects the appropriate fusion algorithm to receive the best image enhancement results for human observers. Assessment of the fusion algorithms' results was done based on the local contrasts. Fusion algorithms are used on a representative data set covering different use cases and image contents. These fusion results of selected data are judged subjectively by some human observers. Then the assessment algorithm with the best fit to the visual perception is used to select the best fusion algorithm for comparable scenarios.

关键词： night vision image fusion assessment algorithm enhancement

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：