检索结果-内蒙古大学图书馆

Utilising Kronecker Decomposition and Tensor-based Multi-view Learning to predict where people are looking in images

引用

NEUROCOMPUTING 2017年 248卷 80-93页

作者： Pasupa, Kitsuchart Szedmak, Sandor King Mongkuts Inst Technol Ladkrabang Fac Informat Technol Bangkok 10520 Thailand Aalto Univ Dept Comp Sci FI-00076 Aalto Finland

Eye movement data collection is very expensive and laborious. Moreover, there are usually missing values. Assuming that we are collecting eye movement data from a set of images viewed by different users, there is a possibility that we will not able to collect the data of every user from every image-one or more views may not be represented in the image. We assume that the relationships among the views can be learnt from the whole collection of views (or items). The task is then to reproduce the missing part of the incomplete items from the relationships derived from the complete items and the known part of these items. Using certain properties of tensor algebra, we showed that this problem can be formulated consistently as a regression type learning task. Furthermore, there is a maximum margin based optimisation framework in which this problem can be solved in a tractable way. This problem is similar to learning to predict where a person is looking in an image. Therefore, we proposed an algorithm called "Tensor-based Multi-view Learning"(TMvL) in this paper. Furthermore, we also proposed a technique for improving prediction by introducing a new feature set obtained from Kronecker decomposition of the image fused with user's eye movement data. Using this new feature can improve prediction performance markedly. The proposed approach was proven to be more effective than two well-known saliency detection techniques. (C) 2017 Elsevier B.v. All rights reserved.

关键词： Multi-view learning Missing data Tensor algebra Maximum margin learning Eye movements Kronecker decomposition

来源：评论

学校读者我要写书评

暂无评论

Integrating data and image Domain Deep Learning for Limited Angle Tomography using Consensus Equilibrium 17

Integrating Data and Image Domain Deep Learning for Limited ...

引用

IEEE/CvF International conference on Computer vision (ICCv)

作者： Ghani, Muhammad Usman Karl, W. Clem Boston Univ Boston MA 02215 USA

ISBN: (纸本)9781728150239

Computed Tomography (CT) is a non-invasive imaging modality with applications ranging from healthcare to security. It reconstructs cross-sectional images of an object using a collection of projection data collected at different angles. Conventional methods, such as FBP, require that the projection data be uniformly acquired over the complete angular range. In some applications, it is not possible to acquire such data. Security is one such domain where non-rotational scanning configurations are being developed which violate the complete data assumption. Conventional methods produce images from such data that are filled with artifacts. The recent success of deep learning (DL) methods has inspired researchers to post-process these artifact laden images using deep neural networks (DNNs). This approach has seen limited success on real CT problems. Another approach has been to pre-process the incomplete data using DNNs aiming to avoid the creation of artifacts altogether. Due to imperfections in the learning process, this approach can still leave perceptible residual artifacts. In this work, we aim to combine the power of deep learning in both the data and image domains through a two-step process based on the consensus equilibrium (CE) framework. Specifically, we use conditional generative adversarial networks (cGANs) in both the data and the image domain for enhanced performance and efficient computation and combine them through a consensus process. We demonstrate the effectiveness of our approach on a real security CT dataset for a challenging 900 limited-angle problem. The same framework can be applied to other limited data problems arising in applications such as electron microscopy, nondestructive evaluation, and medical imaging.

关键词： Computational imaging Computed tomography Consensus equilibrium data domain learning Deep imaging Deep learning image domain learning incomplete data Learned imaging Limited data Model based image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Average Consistency: A Superior Way of Using the Composite image to Boost Dynamic CT reconstruction

Average Consistency: A Superior Way of Using the Composite I...

引用

conference on Medical Imaging - Physics of Medical Imaging

作者： Tao, Xi Wang, Yongbo Hong, Zixuan Fu, Shuai Zhang, Hua Ma, Jianhua Southern Med Univ Sch Biomed Engn Guangzhou 510515 Guangdong Peoples R China

ISBN: (纸本)9781510633926

Dynamic imaging (such as computed tomography (CT) perfusion, dynamic CT angiography, dynamic positron emission tomography, four-dimensional CT, etc.) is widely used in the clinic. The multiple-scan mechanism of dynamic imaging results in greatly increased radiation dose and prolonged acquisition time. To deal with these problems, low-mAs or sparse-view protocols are usually adopted, which lead to noisy or incomplete data for each frame. To obtain high-quality images from the corrupted data, a popular strategy is to incorporate the composite image that reconstructed using the full dataset into the iterative reconstruction procedure. Previous studies have tried to enforce each frame to approach the composite image in each iteration, which, however, introduces mixed temporal information into each frame. In this paper, we propose an average consistency (AC) model for dynamic CT image reconstruction. The core idea of AC is to enforce the average of all frames to approach the composite image in each iteration, which preserves image edges and noise characteristics while avoids the invasion of mixed temporal information. Experiment on a dynamic phantom and a patient for CT perfusion imaging shows that the proposed method obtains the best qualitative and quantitative results. We conclude that the AC model is a general framework and a superior way of using the composite image for dynamic CT reconstruction.

关键词： Computed tomography Dynamic imaging image reconstruction Average consistency Composite image

来源：评论

学校读者我要写书评

暂无评论

Dynamic SPECT imaging using a single camera rotation (dSPECT)

引用

IEEE TRANSACTIONS ON NUCLEAR SCIENCE 1999年第4期46卷 1055-1061页

作者： Farncombe, T Celler, A Noll, D Maeght, J Harrop, R Univ British Columbia Dept Phys Vancouver BC Canada Vancouver Hosp & Hlth Sci Ctr Div Nucl Med Vancouver BC V5Z 1M9 Canada Univ Toulouse 3 Lab Math Ind & Phys F-31062 Toulouse France

Techniques to estimate dynamic parameters from the data acquired during a single rotation of a standard (single, dual and triple head) SPECT camera are being investigated. The performance of the constrained linear least squares (C-LS) method is being assessed. This method uses a simple assumption that the activity within each pixel at a given projection angle is less than or equal to the activity seen at the prior angle. In simulations, we have used an analytical heart model with single and bi-exponential activity decrease, with and without background activity and statistical noise in the data. Studies using a single, a 90 degrees dual and a 120 degrees triple head camera were modeled with a total acquisition time of 20min, performing rotation over 180 degrees. These simulations were followed by experimental scans of our dynamic phantom used with and without attenuation and subsequently a preliminary study involving a human subject was performed. Dynamic images from simulations and phantom experiments reconstruct well with an accuracy of reconstructed half-lives for most reconstructions within a 20% en or range. Some streaking artifacts which are evident in images corresponding to early reconstruction times subside upon incorporating further constraints and regularizations.

关键词： Computerized tomography Medical imaging data acquisition Parameter estimation Optical rotation Least squares approximations Mathematical models Computer simulation Cameras Photons image reconstruction Error analysis Single photon emission computed tomography (SPECT) Parameter estimation simulating Medical imaging image reconstruction acquisition time human subject Cameras X-Ray Computed Tomography Photon

来源：评论

学校读者我要写书评

暂无评论

Aspects of binary image reconstruction from Fourier amplitude data

Aspects of binary image reconstruction from Fourier amplitud...

引用

2008 23rd International conference image and vision Computing New Zealand, IvCNZ

作者： Lo, v.L. Millane, R.P. Computational Imaging Group Department of Electrical and Computer Engineering University of Canterbury Private Bag 4800 Christchurch New Zealand

The reconstruction of a binary image from under sampled Fourier amplitude data is considered. Binary, connectivity, and compactness constraints are discussed and shown to he sufficient to enforce a unique solution. An... 详细信息

ISBN: (纸本)9781424425822

关键词： X ray crystallography

来源：评论

学校读者我要写书评

暂无评论

Regularisation of the limited data computed tomography problem via the boundary element method

Regularisation of the limited data computed tomography probl...

引用

International conference on image Processing

作者： Solo, v MACQUARIE UNIV DEPT STATSYDNEYNSW 2109AUSTRALIA

ISBN: (纸本)0780331222

We present a new variational approach to the problem of computed tomography reconstruction from sparse data. We use a Tikhonov regularisation (quite different from that of Louis [1985]) which deals without approximation with discrete or nonuniform grids. Our algorithm requires calculation of a Green's function on a finite region and we show how this can be done very efficiently computationally using the numerical/analytic boundary element method (BEM).

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Integration of Depth Normal Consistency and Depth Map Refinement for MvS reconstruction 17th

Integration of Depth Normal Consistency and Depth Map Refine...

引用

17th Chinese conference on image and Graphics Technologies and Applications, IGTA 2022

作者： Yang, Lifang Bai, Zhengyao Liu, Huijie School of Information Science and Engineering Yunnan University Kunming650500 China

ISBN: (纸本)9789811950957

To address the problem of incomplete Multi-view Stereo (MvS) reconstruction, the initial depth and loss function of the depth residual iterative network are investigated, and a new multi-view stereo reconstruction network integrating depth normal consistency and depth map thinning is presented. Firstly, downsampling the input image to create an image pyramid and extracting a feature map from the image pyramid;Then, constructing a cost volume from the 2D feature map, adding the depth normal consistency to the initial cost volume to optimize the depth map. On the DTU data set, the network is tested and compared to traditional reconstruction approaches and MvS networks based on deep learning. The experimental results show that the proposed MvS reconstruction network was produced the better results in completeness and increased the quality of MvS reconstruction. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Reconstructing magnetic resonance spectroscopic image using spatial domain prior

Reconstructing magnetic resonance spectroscopic image using ...

引用

The 1994 1st IEEE International conference on image Processing

作者： Stokely, E.M. Twieg, D. Department of Biomedical Engineering BEC 256 University of Alabama at Birmingham BirminghamAL35294-4461 United States

Magnetic resonance spectroscopic (MRS) images are low in resolution and often contain low frequency artifacts due to Fourier reconstruction of incomplete sets of data in k (frequency) space. The problem of improving MRS reconstructions can be approached in several ways, resulting in a number of apparently different formulations. These include the extrapolation of missing data samples, and also model-based methods that incorporate prior information from both the spatial and frequency domains. Model-based approaches can be shown to belong to a well-known class of image restoration problems. In the paper, the general MRS image reconstruction problem is reviewed, several approaches to the solution are given, and a particular method is presented that uses finite element models to embed spatial domain priors. © 1994 IEEE.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Semiconducting bilinear deep learning for incomplete image recognition 12

Semiconducting bilinear deep learning for incomplete image r...

引用

2nd ACM International conference on Multimedia Retrieval, ICMR 2012

作者： Zhong, Sheng-Hua Liu, Yan Chung, Fu-Lai Wu, Gangshan Department of Computing Hong Kong Polytechnic University Hong Kong Hong Kong Department of Computer Science and Technology Nanjing University Nanjing China

ISBN: (纸本)9781450313292

image recognition with incomplete data is a well-known hard problem in multimedia content analysis. This paper proposes a novel deep learning technique called semiconducting bilinear deep belief networks (SBDBN) by referencing human's visual cortex and intelligent perception. Inheriting from deep models, SBDBN simulates the laminar structure of human's cerebral cortex and the neural loop in human's visual areas. To address the special difficulties of image recognition with incomplete data, we design a novel second-order deep architecture with semiconducting restricted boltzmann machines. Moreover, two peaks activation of human's perception is implemented by three learning stages of semiconducting bilinear discriminant initialization, greedy layer-wise reconstruction, and global finetuning. Owing to exploiting the embedding information according to the reliable features rather than any completion of missing features, the proposed SBDBN has demonstrated outstanding recognition ability on two standard datasets and one constructed dataset, comparing with both incomplete image recognition techniques and existing deep learning models. Copyright © 2012 ACM.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

Single-view 3D Object reconstruction from Shape Priors in Memory

Single-View 3D Object Reconstruction from Shape Priors in Me...

引用

IEEE/CvF conference on Computer vision and Pattern Recognition (CvPR)

作者： Yang, Shuo Xu, Min Xie, Haozhe Perry, Stuart Xia, Jiahao Univ Technol Sydney Sch Elect & Data Engn Sydney NSW Australia Harbin Inst Technol Harbin Peoples R China

ISBN: (纸本)9781665445092

Existing methods for single-view 3D object reconstruction directly learn to transform image features into 3D representations. However, these methods are vulnerable to images containing noisy backgrounds and heavy occlusions because the extracted image features do not contain enough information to reconstruct high-quality 3D shapes. Humans routinely use incomplete or noisy visual cues from an image to retrieve similar 3D shapes from their memory and reconstruct the 3D shape of an object. Inspired by this, we propose a novel method, named Mem3D, that explicitly constructs shape priors to supplement the missing information in the image. Specifically, the shape priors are in the forms of "image-voxel" pairs in the memory network, which is stored by a well-designed writing strategy during training. We also propose a voxel triplet loss function that helps to retrieve the precise 3D shapes that are highly related to the input image from shape priors. The LSTM-based shape encoder is introduced to extract information from the retrieved 3D shapes, which are useful in recovering the 3D shape of an object that is heavily occluded or in complex environments. Experimental results demonstrate that Mem3D significantly improves reconstruction quality and performs favorably against state-of-the-art methods on the ShapeNet and Pix3D datasets.

关键词： Training visualization Three-dimensional displays Shape Transforms Writing Feature extraction

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：