检索结果-内蒙古大学图书馆

16th International conference on Signal-image Technology and Internet-Based Systems (SITIS)

作者： Ayad, Ishak Tarpau, Cecilia Cebeiro, Javier Nguyen, Mai K. CY Cergy Paris Univ ETIS UMR 8051 Cergy Pontoise France CY Cergy Paris Univ CNRS ENSEA AGM UMR 8088 Cergy Pontoise France Heriot Watt Univ Maxwell Inst Math Sci Sch Math & Comp Sci Edinburgh Scotland Univ Nacl San Martin Ctr Matemcit Aplicada Inst Tecnol Ciencias Aplicadas ITECA UNSAM CONICETEscuela Ciencia & Tecnol Buenos Aires Argentina CY Cergy Paris Univ ENSEA CNRS ETIS UMR 8051 Cergy Pontoise France

ISBN: (纸本)9781665464956

Limited-angle and sparse-view computed tomography have been widely used to shorten the acquisition time in medical imaging and to offer the possibility of scanning large objects. However, this is a severely ill-posed inverse problem due to missing data. In these scenarios, the well-known filtered back-projection reconstruction technique exhibits severe artifacts and degradation. Recently, deep learning methods have demonstrated impressive performance in computer vision (denoising, classification, etc.) but it frequently fails to solve both limited-angle and sparse-view reconstruction. Inspired by the high performance of GAN-based image-to-image translation methods, we investigate a patchGAN as a solution to the reconstruction problem mapping data (Radon space) into the image domain. The generator is made of a v-net where the reconstruction in the sense of a least-squares minimization is carried out at different scales in the encoder path and linked with the decoder path by skip connections. The discriminator uses both information from the image and projection data domains. The proposed method gives promising reconstruction results from data acquired with a limited angular range covering only 110 degrees (instead of 180 degrees), as well as for sparse-view data with 10 degrees of sampling step. Moreover, different reconstruction results show that the method is able to reconstruct images from sparse and limited angular range data at the same time.

关键词： computed tomography (CT) generative adversarial networks (GAN) image reconstruction inverse problem hybrid representations

来源：评论

学校读者我要写书评

暂无评论

image reconstruction from LIMITED ANGLE PROJECTIONS: A LINEAR PREDICTION APPROACH.

IMAGE RECONSTRUCTION FROM LIMITED ANGLE PROJECTIONS: A LINEA...

引用

Proceedings of the Eighth Annual conference of the IEEE/Engineering in Medicine and Biology Society.

作者： Srinivasa, N. Krishnan, v. Ramakrishnan, K.R. Rajgopal, K. Indian Inst of Science Bangalore India Indian Inst of Science Bangalore India

One approach to the problem of image reconstruction from projections available over a limited range of views, is to estimate the missing projections by means of data extrapolation and then use a fast algorithm for reconstruction. The use of linear prediction models for estimating the missing projections is proposed. The autoregressive (AR) model has been chosen because of its simplicity in estimating the parameters and its duality with the maximum entropy method. A variety of methods exists for estimating the AR parameters. Three such methods are investigated and it is shown that better reconstruction be obtained by using the convolution backprojection method from the augmented data.

关键词： image PROCESSING

来源：评论

学校读者我要写书评

暂无评论

A problem of emphasizing features of a surface roughness by means the Discrete Wavelet Transform

引用

JOURNAL OF MATERIALS PROCESSING TECHNOLOGY 2005年 164卷 1410-1415页

作者： Niola, v Nasti, G Quaremba, G Univ Naples Federico II Dept Mech Engn Energet Naples Italy

When we are interested to the detection of the roughness features by means of the 3D reconstruction, based on photometric stereo techniques, an important problem is the elimination of the brightness variation due to different light conditions which can alter the response. This paper will concentrate on presenting results of a new method for eliminating this problem. Every pixel of a picture gives only one number: the brightness of the corresponding point on the object, whereas the surface orientation is described by a normal vector that has two degrees of freedom. The level of brightness depends on many factors as well as the homogeneity of reflection properties of the material or its physical continuity and the surface smoothness or roughness. In this work we will show how the application of the Discrete Wavelet Transform (DWT) to the processing of some images, captured on different light conditions, permits to solve the problem of emphasizing roughness features of a metallic surface. Wavelet transforms can model irregular data patterns such as sharp changes, better than the Fourier transforms and standard statistical procedures (e.g., parametric and non-parametric regressions) and provide a multiresolution approximation to the data. Here we propose, also, a non-parametric method, based on the wavelet theory, for the estimation of the threshold level of a gray levels distribution, obtained from the intensity image matrix. (c) 2005 Elsevier B.v. All rights reserved.

关键词： image processing surface roughness wavelet transform optimum threshold

来源：评论

学校读者我要写书评

暂无评论

Sparse Range-Doppler image Construction with Neural Networks

Sparse Range-Doppler Image Construction with Neural Networks

引用

IEEE International Radar conference (RADAR)

作者： Akhtar, Jabran Norwegian Def Res Estab FFI Kjeller Norway

ISBN: (数字)9781728168135

ISBN: (纸本)9781728168135

The principles outlined by compressed sensing can permit a sensor to collect reduced amount of data and still reconstruct an exact outcome. This can for example be used to generate super-resolution sparse range-Doppler radar images while emitting a reduced number of pulses within a coherent processing interval. In this paper, we investigate the use of neural networks as a mean to solve the sparse reconstruction problem with specific emphasis towards range-Doppler images. The neural networks are trained to generate a sparse Doppler profile from incomplete time domain data in line with traditional sparse L-1-norm minimization. We show that this approach is viable through fully connected feed forwarding networks and the results closely mimic sparse recovered range-Doppler maps.

关键词： Range-Doppler discrete Fourier transform compressed sensing sparse reconstruction neural networks

来源：评论

学校读者我要写书评

暂无评论

image Quality Assessment for Extended-volume C-arm CT Using a Multi-Turn Reverse Helix

Image Quality Assessment for Extended-Volume C-arm CT Using ...

引用

IEEE Nuclear Science Symposium / Medical Imaging conference (NSS/MIC)

作者： Yu, Z. Maier, A. Lauritsch, G. vogt, F. Schoenborn, M. Koehler, C. Hornegger, J. Noo, F. Univ Utah Dept Radiol Salt Lake City UT 84112 USA Friedrich Alexander Univ Erlangen Nuremberg Pattern Recognit Lab Bavaria Germany Siemens AG Healthcare Bavaria Germany

ISBN: (纸本)9781479960972

C-arm computed tomography (CT) with axially extended field-of-view is valuable when imaging a long organ is desired in the interventional room. However, current C-arm CT employs a circular short scan that only provides incomplete data and short axial coverage. To enable long-object 3D imaging capability on a C-arm system, a multi-turn reverse helix is an attractive solution for data acquisition. We have implemented this trajectory on a state-of-the-art multi-axis C-arm system and performed image reconstruction using our Fusion-RFDK method. This work evaluates these reconstruction results by comparing them with those obtained from a circular short scan. We observed comparable image quality between the two source trajectories.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Client-driven Transmission of JPEG2000 image Sequences using Motion Compensated Conditional Replenishment

Client-driven Transmission of JPEG2000 Image Sequences using...

引用

data Compression conference (DCC)

作者： Sanchez-Hernandez, J. J. Gonzalez-Ruiz, v Garcia-Ortiz, J. P. Mueller, D. Univ Almeria Ctra Sacramento S-N Almeria 04120 Spain European Space Agcy Estec POB 299 NL-2200 AG Noordwijk Netherlands

ISBN: (纸本)9781728106571

This is a work focused on remote browsing of JPEG2000 image sequences which takes advantage of the spatial scalability of JPEG2000 to determine which precincts of a subsequent image should be transmitted, and which precincts should be reused from a previously reconstructed image. The results of our experiments demonstrate that the quality of the reconstructed images can be significantly increased by using motion compensation and conditional replenishment on the client side. The proposed algorithm is compatible with standard JPIP servers.

关键词： Transform coding Servers image sequences Proposals image reconstruction image coding Motion compensation

来源：评论

学校读者我要写书评

暂无评论

image decoding optimization based on compressive sensing

引用

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS 2011年第5期236卷 812-818页

作者： Zhang, Zhen Shi, Yunhui Kong, Dehui Ding, Wenpeng Yin, Baocai Beijing Univ Technol Coll Comp Sci & Technol Beijing Municipal Key Lab Multimedia & Intelligen Beijing 100124 Peoples R China

Transform-based image codec follows the basic principle: the reconstructed quality is decided by the quantization level. Compressive sensing (CS) breaks the limit and states that sparse signals can be perfectly recovered from incomplete or even corrupted information by solving convex optimization. Under the same acquisition of images, if images are represented sparsely enough, they can be reconstructed more accurately by CS recovery than inverse transform. So, in this paper, we utilize a modified Tv operator to enhance image sparse representation and reconstruction accuracy, and we acquire image information from transform coefficients corrupted by quantization noise. We can reconstruct the images by CS recovery instead of inverse transform. A CS-based JPEG decoding scheme is obtained and experimental results demonstrate that the proposed methods significantly improve the PSNR and visual quality of reconstructed images compared with original JPEG decoder. (C) 2011 Elsevier B.v. All rights reserved.

关键词： Compressive sensing image decoding Total variation SOCP

来源：评论

学校读者我要写书评

暂无评论

Evaluation and optimization of the maximum-likelihood approach for image reconstruction in digital breast tomosynthesis

Evaluation and optimization of the maximum-likelihood approa...

引用

conference on Medical Imaging - Physics of Medical Imaging

作者： Jerebko, Anna K. Mertelmeier, Thomas Siemens AG Healthcare D-91050 Erlangen Germany

ISBN: (纸本)9780819480231

Digital Breast Tomosynthesis* (DBT) suffers from incomplete data and poor quantum statistics limited by the total dose absorbed in the breast. Hence, statistical reconstruction assuming the photon statistics to follow a Poisson distribution may have some advantages. This study investigates state-of-art iterative maximum likelihood (ML) statistical reconstruction algorithms for DBT and compares the results with simple backprojection (BP), filtered backprojection (FBP), and iFBP (FBP with filter derived from iterative reconstruction). The gradient-ascent and convex optimization variants of the transmission ML algorithm are evaluated with phantom and clinical data. Convergence speed is very similar for both iterative statistical algorithms and after approximately 5 iterations all significant details are well displayed, although we notice increasing noise. We found empirically that a relaxation factor between 0.25 and 0.5 provides the optimal trade-off between noise and contrast. The ML-convex algorithm gives smoother results than the ML-gradient algorithm. The low-contrast CNR of the ML algorithms is between CNR for simple backprojection (highest) and FBP (lowest). Spatial resolution of iterative statistical and iFBP algorithms is similar to that of FBP but the quantitative density representation better resembles conventional mammograms. The iFBP algorithm provides the benefits of statistical iterative reconstruction techniques and requires much shorter computation time.

关键词： tomosynthesis iterative reconstruction statistical reconstruction filtered backprojection breast imaging mammography

来源：评论

学校读者我要写书评

暂无评论

DualGAN: Unsupervised Dual Learning for image-to-image Translation 16

DualGAN: Unsupervised Dual Learning for Image-to-Image Trans...

引用

16th IEEE International conference on Computer vision (ICCv)

作者： Yi, Zili Zhang, Hao Tan, Ping Gong, Minglun Mem Univ Newfoundland St John NF Canada Simon Fraser Univ Burnaby BC Canada

ISBN: (纸本)9781538610329

Conditional Generative Adversarial Networks( GANs) for cross-domain image-to-image translation have made much progress recently [7, 8, 21, 12, 4, 18]. Depending on the task complexity, thousands to millions of labeled image pairs are needed to train a conditional GAN. However, human labeling is expensive, even impractical, and large quantities of data may not always be available. Inspired by dual learning from natural language translation [23], we develop a novel dual-GAN mechanism, which enables image translators to be trained from two sets of unlabeled images from two domains. In our architecture, the primal GAN learns to translate images from domain U to those in domain v, while the dual GAN learns to invert the task. The closed loop made by the primal and dual tasks allows images from either domain to be translated and then reconstructed. Hence a loss function that accounts for the reconstruction error of images can be used to train the translators. Experiments on multiple image translation tasks with unlabeled data show considerable performance gain of DualGAN over a single GAN. For some tasks, DualGAN can even achieve comparable or slightly better results than conditional GAN trained on fully labeled data.

关键词： Gallium nitride Generators image reconstruction Training data Training Computer vision

来源：评论

学校读者我要写书评

暂无评论

reconstruction of simulated vLBI data using the SARA method and random raw patches

Reconstruction of simulated VLBI data using the SARA method ...

引用

2023 International conference on Computer Science, Information Technology and Engineering, ICCoSITE 2023

作者： Atmaja, Ratri Dwi Suksmono, Andriyan Bayu Danudirdjo, Donny Hidayat, Taufiq Institut Teknologi Bandung School of Electrical Engineering and Informatics School of Electrical Engineering Telkom University Bandung Indonesia Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia Institut Teknologi Bandung Faculty of Mathematics and Natural Sciences Bandung Indonesia

ISBN: (纸本)9798350320954

vLBI (very long baseline interferometry) is used to image astronomical objects. However, the image quality decreases due to incomplete visibility measurements. The visibility is affected by the frequency, baseline length, measurement duration, and some telescopes used. A popular method that can solve this quality degradation problem in vLBI is SARA (sparsity averaging reweighted analysis). This study aims to increase the SARA performance with scoped in improving NRMSE (normalized root mean square error) and SNR (signal-to-noise ratio) on simulated vLBI data. We used random raw patch pairs from the SARA results to get a trained dictionary. In collecting the data for training, we used ten original images of the surrounding objects that we captured. Then we measured it using a vLBI sampling pattern, processed it using SARA, and applied the SARA results as a pre-reconstruction image. After that, we trained these ten pairs of the original and pre-reconstruction images. In reconstruction, we used the dictionary to test two simulated data and compare the results with the SARA. Finally, the results showed that the combination of SARA and random raw patches had a smaller NRMSE and a higher SNR than the SARA alone. © 2023 IEEE.

关键词： image reconstruction

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：