检索结果-内蒙古大学图书馆

Annual conference on Information Sciences and Systems (CISS)

作者： Daniel S. Weller University of Virginia Charlottesville VA US

ISBN: (纸本)9781509026975

This talk describes a new adaptive variant of K-SvD dictionary learning that is suitable for the highly varied features present in MRI images. This variant is used to regularize SPIRiT parallel MRI reconstruction to produce higher quality images from incomplete measurements. The approach described involves modeling the dictionary approximation error as nearly sparse across the patches of the reconstructed image. This presentation will feature experiments reconstructing MRI data from multiple types of scans, including neuroimaging and cardiac imaging. These results demonstrate that the proposed method yields better reconstruction quality in both these settings. This talk will conclude with a discussion of related challenges in MRI reconstruction.

关键词： image reconstruction Magnetic resonance imaging Dictionaries Acceleration Computers Adaptation models Approximation error

来源：评论

学校读者我要写书评

暂无评论

MR image reconstruction from data Acquired on an Irregular K-space trajectory 36

MR Image Reconstruction from Data Acquired on an Irregular <...

引用

36th IEEE International conference on Electronics and Nanotechnology (ELNANO)

作者： Gavrilyuk, v. S. Netreba, A., v Radchenko, S. P. Taras Shevchenko Natl Univ Kyiv Fac Radiophys Elect & Comp Syst Kiev Ukraine

ISBN: (纸本)9781509014316

The reconstruction for the magnetic resonance imaging under condition of using irregular measured signal data array for reconstructing of the spine density spatial distribution are offered. For experimentally measured data using a Fourier-Zymography in Magnetic Resonance Imaging techniques simulated the received signal and realised the reverse reconstruction of tomograms. The evaluation of the quality of tomograms with incomplete signal data set has been carried out.

关键词： Magnetic resonance imaging reconstruction K-space incomplete data

来源：评论

学校读者我要写书评

暂无评论

METHOD AND SYSTEM FOR SYNCHRONISING vIDEO AND data

METHOD AND SYSTEM FOR SYNCHRONISING VIDEO AND DATA

引用

作者： MOLINAS LOMBART, Eloi ANDRéS MORáN, ángel

标准号: WO2017137358(A1)

The method comprises: - generating a marked video signal by extracting an image fragment (v) from a region (R) of an original frame (F), and arranging a watermark (M) thereon;and - generating a data signal, including therein the extracted image fragment extracted (v) and/or reconstruction information;- performing an additional synchronisation step, which comprises: - obtaining, from the data signal, the image fragment (v) and/or the reconstruction information, - obtaining, from the marked video signal, an incomplete frame (Fr), and - attempting to reconstruct the original frame (F) from the information obtained from the data signal and the marked video signal, and, if the reconstruction is successful, determining that the synchronisation is correct. The system is adapted to implement the method of the invention.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Deep Learning of Foreground, Background and Shape for Robust Contextual Segmentation 25th

Joint Deep Learning of Foreground, Background and Shape for ...

引用

25th Biennial International conference on Information Processing in Medical Imaging (IPMI)

作者： Ravishankar, Hariharan Thiruvenkadam, S. venkataramani, R. vaidya, v. GE Global Res Bangalore Karnataka India

ISBN: (纸本)9783319590509;9783319590493

Encouraged by the success of CNNs in classification problems, CNNs are being actively applied to image-wide prediction problems such as segmentation, optic flow, reconstruction, restoration etc. These approaches fall under the category of fully convolutional networks [FCN] and have been very successful in bringing contexts into learning for image analysis. In this work, we address the problem of segmentation from medical images. Segmentation or object delineation from medical images/volumes is a fundamental step for subsequent quantification tasks key to diagnosis. Semantic segmentation has been popularly addressed using FCN (e.g. U-NET) with impressive results and has been the fore runner in recent segmentation challenges. However, there are a few drawbacks of FCN approaches which recent works have tried to address. Firstly, local geometry such as smoothness and shape are not reliably captured. Secondly, spatial context captured by FCNs while giving the advantage of a richer representation carries the intrinsic drawback of overfitting, and is quite sensitive to appearance and shape changes. To handle above issues, in this work, we propose a hybrid of generative modeling of image formation to jointly learn the triad of foreground (F), background (B) and shape (S). Such generative modeling of F, B, S would carry the advantages of FCN in capturing contexts. Further we expect the approach to be useful under limited training data, results easy to interpret, and enable easy transfer of learning across segmentation problems. We present similar to 8% improvement over state of art FCN approaches for US kidney segmentation and while achieving comparable results on CT lung nodule segmentation.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

The study of effectiveness of a high-performance crystal lattice parametric identification algorithm based on CUDA technology

引用

Journal of Physics: conference Series 2019年第5期1368卷

作者： Shirokanev, A S Kirsh, D v Kupriyanov, A v Samara National Research University Moskovskoe Shosse 34A Samara Russia 443086 Image Processing Systems Institute of RAS - Branch of the FSRC “Crystallography and Photonics” RAS Molodogvardejskaya street 151 Samara Russia 443001

The study of substances with a crystal structure is a complex multi-step process. The key step in the crystalline substance analysis is the unit cell parameter estimation. The estimation of the crystal lattice unit cell parameters is a particular problem that involves the search of the crystal lattice model’s parameters according to the information which can be extracted from the substance. In these recent times, the most accurate information about the substance structure can be obtained with the electron microscope whose linear resolution is high enough to observe the atomic structure of a substance. The problem of parameter estimation in this case means the reconstruction of the three-dimensional crystal lattice with 2-dimentional images received by an electron microscope, and the estimation of the crystal lattice unit cell parameters by reconstructed lattice. In the previous papers the crystal lattice parametric identification algorithms based on solving the local optimization problem were presented. However, the analysis of a large crystal lattice database requires a lot of computations. In this paper, a high-performance crystal lattices parametric identification algorithm using the CUDA technology is proposed. The investigation of the algorithm effectiveness is carried out on the GPU GeForce Nvidia GTX 1070 Ti. With data dimension more than 32 translations the acceleration is higher than 70. The algorithm runs more efficiently at the use of a large number of CUDA-blocks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of patterns for image-based 3D model reconstruction of textureless objects

Performance evaluation of patterns for image-based 3D model ...

引用

International conference on 3D Imaging (IC3D)

作者： Jahanzeb Hafeez Alaric Hamacher SoonChul Kwon SeungHyun Lee Graduate School of Information Contents Kwangwoon University Seoul Korea Department of Computer Science Gachon University Seongnam Korea

This paper evaluates the performance of patterns used to solve a very challenging problem in close range photogrammetry and computer vision when the surface of the object or scene is textureless. Three dimensional surface modeling from arbitrary viewpoints is an active field of research due to its wide range of applications. However, structure-from-motion, a common approach for surface modeling of the objects that are not well textured fails due to insufficient discriminative features in the images and hence results in incomplete and inaccurate three dimensional model of the surface. Mainly, two approaches have been used widely for 3D reconstruction of such kind of objects. First uses a structured light or coded pattern, and second uses a random pattern that provides artificial markers on the surface of interesting object. In this paper, second approach is implemented that helps point-based features, such as SIFT, to find discriminative features from arbitrary viewpoints taken from the same object surface. We evaluate the performance of patterns with respect to quality of reconstruction of the surface of a textureless object. At the end, a comparison scheme between reconstructed model and the ground truth data is also presented and results are evaluated.

关键词： Solid modeling Three-dimensional displays Computational modeling Surface reconstruction image reconstruction Surface texture image color analysis

来源：评论

学校读者我要写书评

暂无评论

COMPRESSIvE image RECOvERY USING RECURRENT GENERATIvE MODEL

COMPRESSIVE IMAGE RECOVERY USING RECURRENT GENERATIVE MODEL

引用

IEEE International conference on image Processing

作者： Akshat Dave Anil Kumar vadathya Kaushik Mitra Indian Institute of Technology Madras Chennai India Indian Institute of Technology Madras Chennai Tamil Nadu IN

reconstruction of signals from compressively sensed measurements is an ill-posed problem. In this paper, we leverage the recurrent generative model, RIDE, as an image prior for compressive image reconstruction. Recurrent networks can model long-range dependencies in images and hence can handle global multiplexing in compressive imaging. We perform MAP inference with RIDE using back-propagation to the inputs and projected gradient method. We propose an entropy thresholding based approach for preserving texture in images well. Our approach shows superior reconstructions compared to recent global reconstruction approaches like D-AMP and TvAL3 on both simulated and real data.

关键词： image reconstruction image coding Entropy Multiplexing Cameras Sensors

来源：评论

学校读者我要写书评

暂无评论

Radioastronomical Least Squares image reconstruction with iteration regularized Krylov subspaces and beamforming-based prior conditioning

Radioastronomical Least Squares image reconstruction with it...

引用

IEEE International conference on Acoustics, Speech and Signal Processing

作者： Shahrzad Naghibzadeh Alle-Jan van der veen Delft University of Technology Netherlands

ISBN: (纸本)9781509041183

A fast iterative method based on projection onto Krylov subspaces has been proposed for Radio Astronomical (RA) image reconstruction from telescope array measurements. The image formation problem is formulated as a linear least squares (LS) estimation problem by discretizing the Field of view (Fov) of the telescope array into a number of pixels. The ill-posed imaging problem is regularized by the Krylov iterations and the system matrix is prior conditioned by the weights attained from the matched filter beamformed data. The performance of the proposed method is shown based on simulated data from a single station of the the Low Frequency Array Radio Telescope (LOFAR) antenna configuration on a test radio astronomical image. It has been shown that the prior conditioning of the system matrix results in a more accurate image estimate by reducing the artifacts introduced in the empty parts of the image. Furthermore, it was shown that Krylov-based methods fit very well in the context of large scale RA image reconstruction due to their speed and computational benefits.

关键词： image formation interferometry regularization radio astronomy Krylov-based imaging image formation radio astronomy telescope array interferometry image reconstruction iterative methods Subspace SINGLE-STATION Least squares method matched filters Conditioning

来源：评论

学校读者我要写书评

暂无评论

Unconventional basement reservoir: from studying to prediction on the example of North-var'Yegansky field

Unconventional basement reservoir: From studying to predicti...

引用

SPE Russian Petroleum Technology conference 2017

作者： Kazakova, Anastasiia S. Rykus, Mikhail v. LLC RN-UfaNIPIneft Russia FSBEI HE Ufa State Petroleum Technological University Russia

As a rule, unconventional reservoirs of pre-Jurassic sequence are characterized by a complex structural and tectonic pattern, sharp variability of net pay thickness and properties. Therefore, using standard approaches often leads to unreliable forecasts. To find effective forecast tools, authors holistically analyze various types of well data and seismic survey, which results in identifying the most efficient tools for studying geological aspects and the way they influence field development, and forecasting. Stages of this work include identifying productive methods for well correlation, core analises, description of thin sections and well log methods and their matching for the purpose of detecting regularities for various rock types using well tests and well performance data. When data were analyzed, the focus was placed on physical properties of reservoir rocks. Besides, the field structure is studied as a whole unit using tectonic history reconstruction. One of the main results of this work is a comprehensive study of the geological development of the upper part of the Paleozoic basement on North-var'yogansky field area for the purpose of a further identification of reservoir extension zones and prediction of well performance depending on rock and void types. Taking into account the new geological image, rock typing is carried out. It is identified that development of rocks with reservoir properties depends on the following factors: primary rock composition, existence of the intake centers of hydrothermal solutions and channels though which they arrived (faults, cracks, fractures) and a set of secondary processes. In the result of this work a complete compliance of well data with seismic survey was achieved. This provided for identification of promising drilling zones and making a plan for geological modeling. Justification of the recommended well logging list and conclusions as to the efficiency of various study methods are important points in studying this kind

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

ISAR reconstruction from incomplete data using Total variation Optimization 5

ISAR Reconstruction from Incomplete Data using Total Variati...

引用

5th Mediterranean conference on Embedded Computing (MECO)

作者： Draganic, Andjela Orovic, Irena Stankovic, Srdjan Li, Xiumei Univ Montenegro Fac Elect Engn Podgorica Montenegro Hangzhou Normal Univ Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781509022212

Sparsity of the TSAR images is exploited with the aim to use the possibility of applying an under-sampling strategy as assumed by the compressive sensing approach. The signal sparsity is a desirable property that needs to be satisfied in order to reconstruct the signals and images from the compressive sensed data. It is assumed that certain amount of radar data is not available and the idea is to reconstruct the radar image from the rest of the data. The signal samples are observed in the spatial domain, and the reconstruction is based on the total variation minimization. The procedure is tested on both, synthetic and real TSAR image, showing satisfactory reconstruction quality with a small set of acquired samples.

关键词： Compressive Sensing ISAR incomplete set of samples TwIST

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：