检索结果-内蒙古大学图书馆

Advances in retinal prosthesis systems

THERAPEUTIC ADvANCES IN OPHTHALMOLOGY 2019年 11卷 2515841418817501-2515841418817501页

作者： Bloch, Edward Luo, Yvonne da Cruz, Lyndon Moorfields Eye Hosp NHS Fdn Trust NIHR Biomed Res Ctr 162 City Rd London EC1V 2PD England UCL Wellcome EPSRC Ctr Intervent & Surg Sci London England East Kent Hosp Univ NHS Fdn Trust Kent England

Retinal prosthesis systems have undergone significant advances in the past quarter century, resulting in the development of several different novel surgical and engineering approaches. Encouraging results have demonstrated partial visual restoration, with improvement in both coarse objective function and performance of everyday tasks. To date, four systems have received marketing approval for use in Europe or the United States, with numerous others undergoing preclinical and clinical evaluation, reflecting the established safety profile of these devices for chronic implantation. This progress represents the first notion that the field of visual restorative medicine could offer blind patients a hope of real and measurable benefit. However, there are numerous complex engineering and biophysical obstacles still to be overcome, to reconcile the gap that remains between artificial and natural vision. Current developments in the form of enhanced image processing algorithms and data transfer approaches, combined with emerging nanofabrication and conductive polymerization techniques, herald an exciting and innovative future for retinal prosthetics. This review provides an update of retinal prosthetic systems currently undergoing development and clinical trials while also addressing future challenges in the field, such as the assessment of functional outcomes in ultra-low vision and strategies for tackling existing hardware and software constraints.

关键词： microelectrode photovoltaic retinal prosthesis tissue electronics

来源：评论

学校读者我要写书评

暂无评论

Mathematical Modeling of the image processing in Television systems

引用

IOP Conference Series: Materials Science and Engineering 2019年第1期680卷

作者： D A Bezuglov v v voronin Russian customs academy Budennovsky 20 Rostov-on-Don 344002 Russia Don State Technical University Gagarin Square 1 Rostov-on-Don 344000 Russia

Modern vision systems include a television image processing system. Improving the technical characteristics and expanding the capabilities of modern devices for recording television images makes it necessary to develop and create highly efficient algorithms for processing television images. Such systems process large amounts of information, therefore, the requirements for the reliability of processing large amounts of data at limited time intervals are constantly increasing. The rapid development of high-performance computing systems has recently created the conditions for expanding the range of tasks that can be solved with the help of vision systems. The research for improving the efficiency of methods and algorithms for digital image processing significant. Currently, the processing of television images is divided into several steps. The first step is the formation of a digital representation of the image (discretization, quantization and input of the image into the computer memory). The second step is the pre-processing of images (restoration and filtering). The third step is the formation of a graphic preparation of the image (segmentation and contour detection). One of the most complex and relevant is the scientific and technical task of the contour detections of objects in television images on the background with additive noise. The purpose of this study is the development of the contour detection method on the image with impulse noise using mathematical modeling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling and Performance Evaluation of Generative adversarial network for image denoising

Modeling and Performance Evaluation of Generative adversaria...

引用

International Conference on Computational Techniques, Electronics and Mechanical systems (CTEMS)

作者： v NUTHNA Kavita Chachadi Leah S Joshi Department of Electrical and Electronics KLE Technological University Hubballi Karnataka

ISBN: (纸本)9781538677100

During transmission and reception the images are degraded by noise. Also images captured using different low quality devices adversely affect the visual quality of images. The presence of the noise results in loss of visibility, gives a mottled, grainy, textured, or snowy appearance. Thus making the image visually unpleasing which drastically affects the human vision. In addition during image processing, presence of noise makes it hard for further processing (impulse, Gaussian white, salt and pepper, adversarial etc.,). Existing methods use conventional filters and Neural network models for image denoising where they compromise with the visibility of image after rigorous iterations of denoising algorithms. In this paper we implement CGANs for image denoising and evaluate the performance of CGAN with different Neural network models viz., CNN ,GAN for single or multiple image denoising problem. The qualitative performance of de-noised image/images is measured using PSNR and confusion matrix.

关键词： Gallium nitride Generators Generative adversarial networks Data models Neural networks Filtering algorithms Noise reduction

来源：评论

学校读者我要写书评

暂无评论

Tiri: A multi-purpose Thermal InfraRed payload for planetary exploration 69

Tiri: A multi-purpose Thermal InfraRed payload for planetary...

引用

69th International Astronautical Congress: #InvolvingEveryone, IAC 2018

作者： Foglia Manzillo, P. BabiÄ‡, L. Esposito, M. Chitu, C.C. Prioroc, C. Canetri, M. Corradi, P. Gil Fernandez, J. Garcia Gutierrez, B. KÃ¼ppers, M. Cosine measurement systems B.V. Oosteinde 26 WarmondNL2361 CH Netherlands GMV Innovating Solutions S.R.L. SkyTower 246C Calea Floreasca Sector 1 BucharestRO014476 Romania 1998-025 Portugal ESA-ESTEC Keplerlaan 1 AG NoordwijkNL-2200 Netherlands ESA-ESAC P. O. Box 78 Villanueva de la CaÃ±ada MadridES28691 Spain

TIRI is a multi-purpose Thermal InfraRed (TIR) imager, initially designed for the Asteroid Impact Mission, an ESA Technology Mission of Opportunity targeting Didymos, a binary near - Earth asteroid. TIRI is conceived to determine asteroid surface physical parameters, such as temperature, thermal inertia, chemical composition, rock shape, and to aid the spacecraft navigation. TIRI takes advantage of the technology developments performed in recent years in TIR sensors, optical manufacturing and materials, electronics, and navigation algorithms. The result is a medium sized payload (~ 11 kg mass and 35 x 30 x 19 cm3 volume) enabling the unprecedented possibility of performing both scientific and navigation tasks. TIRI integrates two optical systems. The first is an imaging line-spectrometer, exhibiting a spatial resolution of few metres and a spectral resolution in the range of tens of nanometres. It allows to determine the asteroid surface temperature with an accuracy of 5 K, to quantitatively evaluate its thermal inertia, and to sample its spectrum with more than 20 bands in the 8 Î¼m - 14 Î¼m range for asteroid composition retrieval. The second TIRI optical head is NavIRâ„¢, a miniaturised thermal infrared navigation camera (less than 1.5 cubic decilitre volume), based on the HyperScoutÂ® design, developed by cosine for ESA under a GSTP contract. It exhibits a fully reflective telescope with a large 2D field of view (as large as 24Â° x 16Â° depending on the chosen sensor). Both optical instruments are integrated in the same mechanical structure and employ uncooled, a-Si, micro-bolometer arrays as detectors. The TIRI electronic system controls both detectors. It is capable to process the acquired frames enhancing their radiometric quality, and to run the navigation algorithms. The NavIRâ„¢ thermal imagery is used by the navigation system to determine the spacecraft position and velocity relative to the asteroid. The employed image processing algorithms (centroid and

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

***: Dissemination platform for deep learning models

arXiv

引用

arXiv 2019年

作者： Hosny, Ahmed Schwier, Michael Berger, Christoph Örnek, Evin P. Turan, Mehmet Tran, Phi v. Weninger, Leon Isensee, Fabian Maier-Hein, Klaus H. McKinley, Richard Lu, Michael T. Hoffmann, Udo Menze, Bjoern Bakas, Spyridon Fedorov, Andriy Aerts, Hugo J.W.L. Program Brigham and Women's Hospital Harvard Medical School BostonMA United States Department of Radiation Oncology Dana-Farber Cancer Institute Harvard Medical School BostonMA United States Department of Radiology Brigham and Women's Hospital Dana-Farber Cancer Institute Harvard Medical School BostonMA United States Harvard Medical School BostonMA United States Institute for Advanced Study Department of Informatics Technical University of Munich Munich Germany Max Planck Institute for Intelligent Systems Stuttgart Germany Booz Allen Hamilton McLeanVA United States Institute of Imaging & Computer Vision RWTH Aachen University Aachen Germany Heidelberg Germany Support Centre for Advanced Neuroimaging University Institute of Diagnostic Interventional Neuroradiology Inselspital Bern University Hospital Bern Switzerland Cardiovascular Imaging Research Center Massachusetts General Hospital Harvard Medical School Boston United States Cardiac MR PET CT Program Department of Radiology Massachusetts General Hospital BostonMA United States Center for Biomedical Image Computing and Analytics University of Pennsylvania PhiladelphiaPA United States Radiology & Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Radiology and Nuclear Medicine GROW CARIM Maastricht University Maastricht Netherlands

Recent advances in artificial intelligence research have led to a profusion of studies that apply deep learning to problems in image analysis and natural language processing among others. Additionally, the availability of open-source computational frameworks has lowered the barriers to implementing state-of-the-art methods across multiple domains. Albeit leading to major performance breakthroughs in some tasks, effective dissemination of deep learning algorithms remains challenging, inhibiting reproducibility and benchmarking studies, impeding further validation, and ultimately hindering their effectiveness in the cumulative scientific progress. In developing a platform for sharing research outputs, we present *** (***), a community-driven container-based software engine and platform for the structured dissemination of deep learning models. For contributors, the engine controls data flow throughout the inference cycle, while the contributor-facing standard template exposes model-specific functions including inference, as well as pre- and post-processing. Python and RESTful Application programming interfaces (APIs) enable users to interact with models hosted on *** and allows both researchers and developers to utilize models out-of-the-box. *** is domain-, data-, and framework-agnostic, catering to different workflows and contributors' preferences. Copyright © 2019, The Authors. All rights reserved.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

image processing system in conditions of uncertainty and the training of its operator

引用

IOP Conference Series: Materials Science and Engineering 2019年第6期537卷

作者： v v Alekseev D v Lakomov A G Maamari A A Shishkin G v Petrukhnova Tambov State Technical University 106 Sovetskaya Street Tambov 392000 Russia Voronezh State Technical University 14 Moscow ave Voronezh Russia

In modern information systems, decision making based on image processing is hampered by the impact of negative external and internal factors leading to image blurring, which introduces uncertainty in this process. In this regard, algorithms and models are used to reduce the effect of uncertainty in image analysis. The article presents a new adaptive algorithm for image processing in different wave bands. The article also presents the results of research on the training of operators of image processing systems in conditions of uncertainty. It is proposed to train the operators of these systems on the basis of a competence-based approach using an information system that allows you to create individual training paths for the operators. The implementation of the training information system is proposed to be made on the basis of a web service.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LSM-W²: laser scanning microscopy worker for wheat leaf surface morphology

引用

BMC systems BIOLOGY 2019年第1-Sup期13卷 22-22页

作者： Zubairova, Ulyana S. verman, Pavel Yu. Oshchepkova, Polina A. Elsukova, Alina S. Doroshkov, Alexey v. RAS SB Inst Cytol & Genet Prospekt Lavrentyeva 10 Novosibirsk 630090 Russia RAS SB AP Ershov Inst Informat Syst Prospekt Lavrentyeva 6 Novosibirsk 630090 Russia Novosibirsk State Univ Pirogova Str 1 Novosibirsk 630090 Russia

BackgroundMicroscopic images are widely used in plant biology as an essential source of information on morphometric characteristics of the cells and the topological characteristics of cellular tissue pattern due to modern computer vision algorithms. High-resolution 3D confocal images allow extracting quantitative characteristics describing the cell structure of leaf epidermis. For some issues in the study of cereal leaves development, it is required to apply the staining techniques with fluorescent dyes and to scan rather large fragments consisting of several frames. We aimed to develop a tool for processing multi-frame multi-channel 3D images obtained from confocal laser scanning microscopy and taking into account the peculiarities of the cereal leaves *** elaborated an imageJ-plugin LSM-W-2 that allows extracting data on Leaf Surface Morphology from Laser Scanning Microscopy images. The plugin is a crucial link in a workflow for obtaining data on structural properties of leaf epidermis and morphological properties of epidermal cells. It allows converting large lsm-files (laser scanning microscopy) into segmented 2D/3D images or tables with data on cells and/or nuclei sizes. In the article, we also represent some case studies showing the plugin application for solving biological tasks. Namely the plugin is applied in the following cases: defining parameters of jigsaw-puzzle pattern for maize leaf epidermal cells, analysis of the pavement cells morphological parameters for the mature wheat leaf grown under control and water deficit conditions, initiation of cell longitudinal rows, and detection of guard mother cells emergence at the initial stages of the stomatal morphogenesis in the growth zone of a wheat *** proposed plugin is efficient for high-throughput analysis of cellular architecture for cereal leaf epidermis. The workflow implies using inexpensive and rapid sample preparation and does not require the applying of transgenesis an

关键词： imageJ plugin Confocal laser scanning microscopy Leaf epidermal pattern image processing Cereals stomata Pavement cells Growth zone

来源：评论

学校读者我要写书评

暂无评论

F-transform-Based Optimization for image Restoration (Inpainting)

F-transform-Based Optimization for Image Restoration (Inpain...

引用

IEEE International Conference on Fuzzy systems

作者： I. Perfilieva University of Ostrava Institute for Research and Applications of Fuzzy Modeling Ostrava 1 Czech Republic

In image processing, the inpainting (image restoration) problem is often considered with respect to the interpolation. We involve into the solution of this problem the F-transform-based nonlocal operators that define a new type of functionals, extending the ability of classical PDE-based algorithms in handling textures and repetitive structures. We showed that in the particular space with a fuzzy partition, the nonlocal Laplacian and partial derivatives can be represented by the F~0- and F~1-transforms. For the inpainting problem specified by relatively large damaged areas, we propose a new total variation model with the F-transform-based nonlocal operators. We show that the proposed model together with the corresponding algorithm increase the quality of a (usually considered) patch-based searching algorithm.

关键词： Transforms image restoration Fuzzy sets Interpolation Partitioning algorithms Hafnium

来源：评论

学校读者我要写书评

暂无评论

A Particle-image velocimetry System for Measurement of velocity Flow Fields for Investigations of Thermohydraulic Processes on the Large-Scale Benchmark of a Promising Fast-Neutron Reactor

引用

INSTRUMENTS AND EXPERIMENTAL TECHNIQUES 2017年第3期60卷 418-427页

作者： Sergeev, D. A. Kandaurov, A. A. Troitskaya, Yu. I. Pakholkov, v. v. Rogozhkin, S. A. Shepelev, S. F. Russian Acad Sci Fed Res Ctr Inst Appl Phys Nizhnii Novgorod 603950 Russia Afrikantov Joint Stock Co Expt Design Bur Mech Engn Nizhnii Novgorod 603074 Russia

The use of visualization techniques in the research on thermohydraulic processes using large-scale models of nuclear power plants is discussed. In particular, the original particle-image velocimetry (PIv) measurement system at the TISEI test bench was presented, which is a model of a proposed fast-neutron reactor. Illumination and video-filming systems with the simultaneous use of several lasers and camcorders, as well as image-processing algorithms that make it possible to carry out field measurements with high precision in a complex configuration of the reactor model, reflections and distortions of the laser knife section, and shadowing by obstacles are described. The developed methodology of conversion of the image coordinates and velocity field into the reference system of the reactor model using a virtual 3D simulation made it possible to significantly simplify the experiments.

关键词： image processing algorithm Fast nuclear reactors flow field particle image velocimetry Camcorders Speed measurement Shadowing (Histology) field measure velocity field reference system thermohydraulics

来源：评论

学校读者我要写书评

暂无评论

Update on k-truss Decomposition on GPU

Update on k-truss Decomposition on GPU

引用

IEEE Conference on High Performance Extreme Computing (HPEC)

作者： Mohammad Almasri Omer Anjum Carl Pearson Zaid Qureshi vikram S. Mailthody Rakesh Nagi Jinjun Xiong Wen-mei Hwu ECE University of Illinois at Urbana-Champaign Urbana IL CS University of Illinois at Urbana-Champaign Urbana IL ISE University of Illinois at Urbana-Champaign Urbana IL Cognitive Computing Systems Research IBM Thomas J. Watson Research Center Yorktown Heights NY

In this paper, we present an update to our previous submission on k-truss decomposition from Graph Challenge 2018. For single k k-truss implementation, we propose multiple algorithmic optimizations that significantly improve performance by up to 35.2x (6.9x on average) compared to our previous GPU implementation. In addition, we present a scalable multi-GPU implementation in which each GPU handles a different `k' value. Compared to our prior multi-GPU implementation, the proposed approach is faster by up to 151.3x (78.8x on average). In case when the edges with only maximal k-truss are sought, incrementing the `k' value in each iteration is inefficient particularly for graphs with large maximum k-truss. Thus, we propose binary search for the `k' value to find the maximal k-truss. The binary search approach on a single GPU is up to 101.5 (24.3x on average) faster than our 2018 k-truss submission. Lastly, we show that the proposed binary search finds the maximum k-truss for “Twitter“ graph dataset having 2.8 billion bidirectional edges in just 16 minutes on a single v100 GPU.

关键词： Graphics processing units Compaction Optimization image edge detection Approximation algorithms Upper bound Hardware

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：