检索结果-内蒙古大学图书馆

conference on image reconstruction from incomplete data vI

作者： Huang, Pin-Yu Chou, Cheng-Ying Natl Taiwan Univ Dept Bioind Mechatron Engn Taipei 106 Taiwan

ISBN: (纸本)9780819482969

X-ray phase-contrast tomography (PCT) methods seek to quantitatively reconstruct separate images that depict an object's absorption and refractive properties. Most PCT reconstruction algorithms generally operate by explicitly or implicitly performing the decoupling of the projected absorption and phase properties at each tomographic view angle by use of a phase-retrieval formula, followed by the inversion of X-ray transform. Tomographic reconstruction by use of statistical methods can account for the noise model and a priori information, and thereby can produce images with better quality over conventional filtered backprojection algorithms. We proposed a weighted least-squares method that takes into account the second-order statistical properties of the projected phase images and aims to minimize the objective function by employing a conjugate-gradient (CG) method. A computer-simulation study was carried out to investigate and evaluate the developed method.

关键词： X-ray phase-contrast tomography noise texture weighted least-squares conjugate-gradient

来源：评论

学校读者我要写书评

暂无评论

Bayesian multiresolution method for local tomography in dental x-ray imaging

引用

PHYSICS IN MEDICINE AND BIOLOGY 2007年第22期52卷 6663-6678页

作者： Niinimaki, K. Siltanen, S. Kolehmainen, v. Univ Kuopio Dept Phys FIN-70211 Kuopio Finland Tampere Univ Technol Inst Math FIN-33101 Tampere Finland

Dental tomographic cone-beam x-ray imaging devices record truncated projections and reconstruct a region of interest (ROI) inside the head. image reconstruction from the resulting local tomography data is an ill-posed inverse problem. A new Bayesian multiresolution method is proposed for local tomography reconstruction. The inverse problem is formulated in a well-posed statistical form where a prior model of the target tissues compensates for the incomplete x-ray projection data. Tissues are represented in a wavelet basis, and prior information is modeled in terms of a Besov norm penalty. The number of unknowns in the reconstruction problem is reduced by abandoning fine-scale wavelets outside the ROI. Compared to traditional voxel-based models, this multiresolution approach allows significant reduction of degrees of freedom without loss of accuracy inside the ROI, as shown by 2D examples using simulated and in vitro local tomography data.

关键词： ELECTRICAL-IMPEDANCE TOMOGRAPHY COMPUTED-TOMOGRAPHY RADON-TRANSFORM STATISTICAL INvERSION ITERATIvE reconstruction ANGLE TOMOGRAPHY NOISE REMOvAL CONvERGENCE RADIOGRAPHS ALGORITHMS Converge Noise cancellation Tomography wavelet basis X-Ray Computed Tomography Bayesian inference algorithms tooth radiography X-Ray Film Radon transforms

来源：评论

学校读者我要写书评

暂无评论

Towards intelligent robust detection of anatomical structures in incomplete volumetric data

引用

MEDICAL image ANALYSIS 2018年 48卷 203-213页

作者： Ghesu, Florin C. Georgescu, Bogdan Grbic, Sasa Maier, Andreas Hornegger, Joachim Comaniciu, Dorin Siemens Healthineers Med Imaging Technol Princeton NJ 08540 USA Friedrich Alexander Univ Erlangen Nurnberg Pattern Recognit Lab Erlangen Germany

Robust and fast detection of anatomical structures represents an important component of medical image analysis technologies. Current solutions for anatomy detection are based on machine learning, and are generally driven by suboptimal and exhaustive search strategies. In particular, these techniques do not effectively address cases of incomplete data, i.e., scans acquired with a partial field-of-view. We address these challenges by following a new paradigm, which reformulates the detection task to teaching an intelligent artificial agent how to actively search for an anatomical structure. Using the principles of deep reinforcement learning with multi-scale image analysis, artificial agents are taught optimal navigation paths in the scale-space representation of an image, while accounting for structures that are missing from the field-of-view. The spatial coherence of the observed anatomical landmarks is ensured using elements from statistical shape modeling and robust estimation theory. Experiments show that our solution outperforms marginal space deep learning, a powerful deep learning method, at detecting different anatomical structures without any failure. The dataset contains 5043 3D-CT volumes from over 2000 patients, totaling over 2,500,000 image slices. In particular, our solution achieves 0% false-positive and 0% false-negative rates at detecting whether the landmarks are captured in the field-of-view of the scan (excluding all border cases), with an average detection accuracy of 2.78 mm. In terms of runtime, we reduce the detection-time of the marginal space deep learning method by 20-30 times to under 40 ms, an unmatched performance for high resolution incomplete 3D-CT data. (C) 2018 Elsevier B.v. All rights reserved.

关键词： Deep learning Deep reinforcement learning Multi-scale detection Scale-space modeling Robust statistical shape-modeling M-estimator sample consensus incomplete 3D-data Real-time detection

来源：评论

学校读者我要写书评

暂无评论

Fundamental limits to noise reduction in images using support - benefits from deconvolution

Fundamental limits to noise reduction in images using suppor...

引用

conference on image reconstruction from incomplete data III

作者： Matson, CL Beckner, CC Schulze, KJ USAF Res Lab Kirtland AFB NM 87117 USA

ISBN: (纸本)0819455008

The usefulness of support constraints to achieve noise reduction in images is analyzed here using an algorithm-independent Cramer-Rao bound approach. Recently, it has been shown that the amount of noise reduction achievable using support as a constraint is a function of the image-domain noise correlation properties. For image-domain delta-correlated noise sources (such as Poisson and CCD read noise), applying a support constraint does not reduce noise in the absence of deconvolution due to the lack of spatial correlation. However, when deconvolution is included in the image processing algorithm, the situation changes significantly because the deconvolution operation imposes correlations in the measurement noise. Here we present results for an invertible system blurring function showing how noise reduction occurs with support and deconvolution. In particular, we show that and explain why noise reduction preferentially occurs at the edges of the support constraint.

关键词： support deconvolution Cramer-Rao bounds image reconstruction noise reduction

来源：评论

学校读者我要写书评

暂无评论

Scattered image reconstruction of Pulsar B0834+06

Scattered image reconstruction of Pulsar B0834+06

引用

conference on image reconstruction from incomplete data vI

作者： Gao, J. J. Rickett, B. J. Coles, W. A. Univ Calif San Diego Dept Elect & Comp Engn La Jolla CA 92037 USA

ISBN: (纸本)9780819482969

The scattered radio image of a pulsar, as a result of the radio wave passing through the turbulent interstellar plasma, is a valuable probe of the plasma turbulence. However the scattering angles are so small, typically a few milli-arcsec, that the radio image cannot be resolved even with very long baseline interferometry (vLBI). Recently we ([1]) combined the secondary spectrum([2]) technique with vLBI astrometry to resolve the ambiguities in reconstructing the scattered image of pulsar B0834+06 at 327 MHz with an angular resolution 100 times finer than would have been possible with vLBI alone. However this technique can only reconstruct the outer portion of the image and it does not provide an estimate of the axial ratio of the plasma turbulence. Here we present a significant advancement of the technique which allows reconstruction of the central part of the image in two dimensions, providing an estimate of the axial ratio of the anisotropic turbulence. This technique relies on modeling a peculiar feature of the two dimensional Fourier transform of the dynamic spectrum (the secondary spectrum), called a "reverse arclet". For the 327 MHz observations of B0834+06 the secondary spectrum exhibits many identical reverse arclets. They originate from the interference between offset bright points and the core of the brightness distribution. The technique has also been tested using simulated data that confirms the image reconstruction algorithm.

关键词： ISM Turbulence image reconstruction Pulsar B0834+06 vLBI Parabolic arcs

来源：评论

学校读者我要写书评

暂无评论

Reconstructing MR images from under- or unevenly-sampled k-space

Reconstructing MR images from under- or unevenly-sampled k-s...

引用

conference on image reconstruction from incomplete data vI

作者： vu, Linda Hajian, Arsen R. Calamai, Paul H. Cenko, Andrew T. Rasheed, Sarbast Kim, Jae K. Piron, Cameron So, Simon S. Meade, Jeff T. Knuth, Kevin H. Univ Waterloo Dept Syst Design Engn 200 Univ Ave W Waterloo ON N2L 3G1 Canada Thunder Bay Reg Res Inst Thunder Bay ON Canada Sentinelle Med Inc Toronto ON Canada SUNY Albany Albany NY 12222 USA

ISBN: (纸本)9780819482969

In MRI, non-rectilinear sampling trajectories are applied in k-space to enable faster imaging. Traditional image reconstruction methods such as a fast Fourier transform (FFT) can not process datasets sampled in non-rectilinear forms (e. g., radial, spiral, random, etc.) and more advanced algorithms are required. The Fourier reduction of optical interferometer data (FROID) algorithm is a novel image reconstruction method(1-3) proven to be successful in reconstructing spectra from sparsely and unevenly sampled astronomical interferometer data. The framework presented allows a priori information, such as the locations of the sampled points, to be incorporated into the reconstruction of images. In this paper, the FROID algorithm has been adapted and implemented to reconstruct magnetic resonance (MR) images from data acquired in k-space where the sampling positions are known. Also, simulated data, including randomly sampled data, are tested and analyzed.

关键词： Random sampling MRI image reconstruction interpolation Fourier transform least squares fit

来源：评论

学校读者我要写书评

暂无评论

Blind deconvolution of speckle images constrained by wavefront sensing data

Blind deconvolution of speckle images constrained by wavefro...

引用

2nd conference on image reconstruction from incomplete data

作者： Leung, WYv Clare, RM Lane, RG Univ Canterbury Dept Elect & Comp Engn Christchurch New Zealand

ISBN: (纸本)0819445592

The predominant effect of the atmosphere on the incoming wavefront of an astronomical object is the introduction of a phase distortion, resulting in,a speckle image at the ground-based telescope. Deconvolution from wavefront sensing is an imaging technique used to compensate for the degradation due to atmospheric turbulence, where the point spread function is estimated from the wavefront sensing data. However in this approach any information in the speckle images regarding the point spread function is not utilised. This paper investigates the joint application of wavefront sensing data and speckle images in reconstructing the point spread function and the object in a Bayesian framework. The results on experimental data demonstrate the feasibility of this approach even under very low light levels.

关键词： blind deconvolution wavefront sensing Shack-Hartmann sensor

来源：评论

学校读者我要写书评

暂无评论

reconstruction from incomplete data IN ECHO DIFFRACTION IMAGING.

RECONSTRUCTION FROM INCOMPLETE DATA IN ECHO DIFFRACTION IMAG...

引用

ICASSP '88: 1988 International conference on Acoustics, Speech, and Signal Processing. v 1, Speech Processing;v 2, Multidimensional Signal Processing;v 3, Digital Signal Processing;v 4, vLSI Spectral Estimation;v 5, Audio & Electroacoustics

作者： Soumekh, Mehrdad State Univ of New York at Buffalo Amherst NY USA State Univ of New York at Buffalo Amherst NY USA

The implications of reconstruction are studied on the basis of measurements of echoed waves from an object. The Helmholtz wave equation model is used for the inversion (diffraction imaging). It is shown that the inverted data provide coverage in one quadrant of the spatial frequency domain. This coverage yields accurate information regarding the surface structure of the object under study.

关键词： image PROCESSING

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional surface approximation from incomplete data using distance transform

Three-dimensional surface approximation from incomplete data...

引用

2nd conference on image reconstruction from incomplete data

作者： Lee, DJ Westover, B Eifert, J Brigham Young Univ Dept Elect & Comp Engn Provo UT 84602 USA

ISBN: (纸本)0819445592

Three-dimensional (3-D) object surface reconstruction is an important step toward non-destructive measurements of surface area and volume. Laser triangulation technique has been widely used for obtaining 3-D information. However, the 3-D data obtained from triangulation are not dense enough or usually not complete for surface reconstruction, especially for objects with irregular shape. As a result of fitting surfaces with these sparse 3-D data, inaccuracy in measuring the surface area or calculating the volume of the object is inevitable. A computer vision technique combining laser triangulation and distance transform has been developed to improve the measurement accuracy for objects with irregular shape. A 3-D wire-frame model is generated first with all available 3-D data. Each pixel within the image boundary is given the distance information using distance transform. The distance information of each pixel is then used as the constraints for surface fitting and interpolation. With this additional information from distance transform, more accurate surface approximation can be achieved. The measurement accuracy of this technique is compared with other interpolation techniques for the volume measurement of oyster meats.

关键词： distance transform laser triangulation 3-D wire-frame model machine vision surface fitting surface interpolation oyster

来源：评论

学校读者我要写书评

暂无评论

Single image Spatially variant Out-of-focus Blur Removal

Single Image Spatially Variant Out-of-focus Blur Removal

引用

conference on image reconstruction from incomplete data vII

作者： Chan, Stanley H. Nguyen, Truong Q. Harvard Univ SEAS 33 Oxford St Cambridge MA 02138 USA UCSD Dept ECE La Jolla CA 92093 USA

ISBN: (纸本)9780819492173

This paper addresses the problem of two-layer out-of-focus blur removal from a single image, in which either the foreground or the background is in focus while the other is out of focus. To recover details from the blurry parts, the existing blind deconvolution algorithms are insufficient as the problem is spatially variant. The proposed method exploits the invariant structure of the problem by first predicting the occluded background. Then a blind deconvolution algorithm is applied to estimate the blur kernel and a coarse estimate of the image is found as a side product. Finally, the blurred region is recovered using total variation minimization, and fused with the sharp region to produce the final deblurred image.

关键词： Blind deconvolution spatially variant total variation alpha-matting kernel estimation depth

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：