检索结果-内蒙古大学图书馆

Color image watermark decoder by modeling quaternion polar harmonic transform with BKF distribution

SIGNAL processing-image COMMUNICATION 2020年 88卷 115946-115946页

作者： Liu, Yunan Zhang, Shanshan Yang, Jian Nanjing Univ Sci & Technol Sch Comp Sci & Engn PCA LabMinist Educ Key Lab Intelligent Percept & Syst High Dimens In Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Lab Image & Video Understanding Socia Nanjing 210094 Peoples R China

It still remains a challenging problem to improve both of the imperceptibility and robustness for the digital image watermarking task. In this study, a color image watermarking scheme is proposed based on quaternion polar harmonic transform (QPHT) with maximum likelihood decoder, which better balances imperceptibility and robustness in a novel fashion. Thanks to the strong robustness of QPHT, the digital watermark is embedded into the QPHT magnitudes using a multiplicative approach. M the receiver, the watermark decoder can be formulated as a problem of weak signal detection, as the QPHT magnitudes are highly non-Gaussian. In view of this, selection of proper models is of great importance to construct a suitable watermark decoder. Further, we validate that the probability density function of Bessel K form suitably models the heavy tail behavior of QPHT magnitudes, and thus the maximum likelihood decoder is developed by modeling QPHT magnitudes with Bessel K form distribution. Experimental results on standard benchmarks demonstrate that the proposed approach provides better imperceptibility and robustness against various kinds of attacks compared to previous state-of-the-art methods.

关键词： Color image watermarking Quaternion polar harmonic transforms Bessel K form distribution Maximum likelihood decoder

来源：评论

学校读者我要写书评

暂无评论

The 16,384-node parallelism of 3D-CNN Training on An Arm CPU based Supercomputer

The 16,384-node Parallelism of 3D-CNN Training on An Arm CPU...

引用

International Conference on High Performance Computing

作者： Akihiro Tabuchi Koichi Shirahata Masafumi Yamazaki Akihiko Kasagi Takumi Honda Kouji Kurihara Kentaro Kawakami Tsuguchika Tabaru Naoto Fukumoto Akiyoshi Kuroda Takaaki Fukai Kento Sato Fujitsu Limited Kawasaki Kanagawa Japan RIKEN Center for Computational Science Kobe Hyogo Japan

ISBN: (纸本)9781665410175

As the computational cost and datasets available for deep neural network training continue to increase, there is a significant demand for fast distributed training on supercomputers. However, porting and tuning applications for new advanced supercomputers requires tremendous amount of development efforts. Therefore, we present software tuning best practice for a 3D-CNN model training on a new Arm CPU based supercomputer, Fugaku. We (i) tune computation in DL by a JIT translator for aarch64, (ii) optimize collective communication such as Allreduce for 6D mesh/torus network topology, (iii) tune I/O by data staging with compression and data loader with caching, and (iv) parallelize training in data and model parallelism. We apply the proposed methods to a CosmoFlow 3D-CNN model, and achieve the training in 30 minutes using 16,384 nodes consisting of 4096 data- and 4 model-parallelism. This is the fastest result of any CPU-based systems in MLPerf HPC v0.7 in the world.

关键词： Training Computational modeling Neural networks parallel processing Supercomputers Software Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Variability and transient search in the SUDARE-VOICE field: a new method to extract the light curves

引用

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 2020年第3期493卷 3825-3837页

作者： Liu, Dezi Deng, Wenqiang Fan, Zuhui Fu, Liping Covone, Giovanni Vaccari, Mattia Radovich, Mario Capaccioli, Massimo De Cicco, Demetra Grado, Aniello Marchetti, Lucia Napolitano, Nicola Paolillo, Maurizio Pignata, Giuliano Ragosta, Fabio Yunnan Univ South Western Inst Astron Res Kunming 650500 Yunnan Peoples R China Shanghai Normal Univ Shanghai Key Lab Astrophys 100 Guilin Rd Shanghai 200234 Peoples R China Yunnan Univ Sch Phys & Astron Kunming 650500 Yunnan Peoples R China INAF Osservatorio Astron Capodimonte Salita Moiariello 16 I-80131 Naples Italy Univ Napoli Federico II Dept Phys Via Cinthia 9 I-80126 Naples Italy INFN Sez Napoli I-80126 Naples Italy Univ Western Cape Dept Phys & Astron Robert Sobukwe Rd ZA-7535 Cape Town South Africa INAF Ist Radioastron Via Gobetti 101 I-40129 Bologna Italy INAF Osservatorio Astron Padova Vicolo Osservatorio 5 I-35122 Padua Italy Millennium Inst Astrophys MAS Santiago 8320000 Chile Pontificia Univ Catolica Chile Inst Astrofis Av Vicuna Mackenna 4860 Santiago 7820436 Chile Univ Cape Town Dept Astron Private Bag X3 ZA-7701 Cape Town South Africa Univ Andres Bello Dept Ciencias Fis Avda Republ 252 Santiago 8320000 Chile

The VLT Survey Telescope (VST) Optical Imaging of the CDFS and ES1 Fields Survey, in synergy with the SUDARE survey, is a deep optical ugri imaging of the CDFS and ES1 fields using the VST. The observations for the CDFS field comprise about 4.38 deg(2) down to r similar to 26 mag. The total on-sky time spans over 4 yr in this field, distributed over four adjacent sub-fields. In this paper, we use the multiepoch r-band imaging data to measure the variability of the detected objects and search for transients. We perform careful astrometric and photometric calibrations and point spread function modelling. A new method, referring to as differential running-average photometry, is proposed to measure the light curves of the detected objects. With the method, the difference of PSFs between different epochs can be reduced, and the background fluctuations are also suppressed. Detailed uncertainty analysis and detrending corrections on the light curves are performed. We visually inspect the light curves to select variable objects, and present some objects with interesting light curves. Further investigation of these objects in combination with multiband data will be presented in our forthcoming paper.

关键词： methods: data analysis methods: observational techniques: image processing techniques: photometric catalogues surveys

来源：评论

学校读者我要写书评

暂无评论

Interactive distributed cloud-based web-server systems for the smart healthcare industry

arXiv

引用

arXiv 2020年

作者： Baurzhanovna, Kondybayeva Almagul National University of Science and Technology MISiS

Subject. This work is dedicated to the questions of the contemporary medical image visualization, the architecture design of the cloud server systems and the using of methods for the .DICOM data representation for the distributed smart healthcare industry ***. In modern medicine and biology, in the pace of research along with the objective need for a constant increase, there is a sharp necessity of the three-dimensional data representation [1]: requiring high-performance methods of the three-dimensional visualization, processing, decomposition, reconstruction and analysis. In many ways, the reason for the sharp growth is associated with the development of the computer technologies (from quantity into quality): the quantitative characteristics of the devices and computers used, the emergence of three-dimensional technologies for processing, visualization and research of data, and, on this basis, the creation of new three-dimensional methods for the human-machine *** methodology. This paper proposes a method for visualization using direct volumetric rendering based on the cubic spline interpolation on a ray emission technology. Modifications of these algorithms, based on a block decomposition, are proposed and still investigated. The server architecture is proposed as a cloud hypervisors server system for the grid processing of the data ***: Data Science for Smart Healthcare, healthcare, internet of things, computer science, interactive visualization, distributed, web-server, cloud, parallel, systems, scientific research, cloud technologies, communications, information, cloud healthcare systems, web-services, web-technologies, information systems, experimental research, DICOM, CT, computed tomography, medical imaging, volume render 2020 MSC: 68-00, 97U99Scope of application. The work aims to investigate the possible contemporary interactive cloud based solutions in the fields of the applied medicine for the smart Healthcare a

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Learning Hierarchical Graph for Occluded Pedestrian Detection 20

Learning Hierarchical Graph for Occluded Pedestrian Detectio...

引用

28th ACM International Conference on Multimedia (MM)

作者： Li, Gang Li, Jian Zhang, Shanshan Yang, Jian Nanjing Univ Sci & Technol Nanjing Peoples R China Tencent Youtu Lab Shenzhen Peoples R China Nanjing Univ Sci & Technol PCA Lab Key Lab Intelligent Percept & Syst High Dimens In Minist Educ Nanjing Peoples R China Nanjing Univ Sci & Technol Jiangsu Key Lab Image & Video Understanding Socia Sch Comp Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9781450379885

Although pedestrian detection has made significant progress with the help of deep convolution neural networks, it is still a challenging problem to detect occluded pedestrians since the occluded ones can not provide sufficient information for classification and regression. In this paper, we propose a novel Hierarchical Graph Pedestrian Detector (HGPD), which integrates semantic and spatial relation information to construct two graphs named intra-proposal graph and inter-proposal graph, without relying on extra cues w.r.t visible regions. In order to capture the occlusion patterns and enhance features from visible regions, the intra-proposal graph considers body parts as nodes and assigns corresponding edge weights based on semantic relations between body parts. On the other hand, the inter-proposal graph adopts spatial relations between neighbouring proposals to provide additional proposal-wise context information for each proposal, which alleviates the lack of information caused by occlusion. We conduct extensive experiments on standard benchmarks of CityPersons and Caltech to demonstrate the effectiveness of our method. On CityPersons, our approach outperforms the baseline method by a large margin of 5.24pp on the heavy occlusion set, and surpasses all previous methods;on Caltech, we establish a new state of the art of 3.78% MR. Code is available at https://***/ligang-cs/PedestrianDetection-HGPD.

关键词： computer vision object detection occluded pedestrian detection graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A New distributed Type-2 Fuzzy Logic Method for Efficient Data Science Models of Medical Informatics

引用

ADVANCES IN FUZZY SYSTEMS 2020年第1期2020卷

作者： Benchara, Fatema Zahra Youssfi, Mohamed Hassan II Univ Casablanca ENSET Mohammedia Lab SSDIA Dept Comp Sci Casablanca Morocco

The paper aims to propose a distributed method for machine learning models and its application for medical data analysis. The great challenge in the medicine field is to provide a scalable image processing model, which integrates the computing processing requirements and computing-aided medical decision making. The proposed Fuzzy logic method is based on a distributed approach of type-2 Fuzzy logic algorithm and merges the HPC (High Performance Computing) and cognitive aspect on one model. Accordingly, the method is assigned to be implemented on big data analysis and data science prediction models for healthcare applications. The paper focuses on the proposed distributed Type-2 Fuzzy Logic (DT2FL) method and its application for MRI data analysis under a massively parallel and distributed virtual mobile agent architecture. Indeed, the paper presents some experimental results which highlight the accuracy and efficiency of the proposed method.

关键词： Health informatics Machine learning Big data Fuzzy Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

DENOISING CONVOLUTIONAL AUTOENCODER BASED B-MODE ULTRASOUND TONGUE image FEATURE EXTRACTION 44

DENOISING CONVOLUTIONAL AUTOENCODER BASED B-MODE ULTRASOUND ...

引用

44th IEEE International Conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Li, Bo Xu, Kele Feng, Dawei Mi, Haibo Wang, Huaimin Zhu, Jian Beijing Univ Posts & Telecommun Automat Dept Beijing 100876 Peoples R China Natl Key Lab Parallel & Distributed Proc Changsha Hunan Peoples R China Natl Univ Def Technol Changsha Hunan Peoples R China Univ Michigan Dept Linguist Ann Arbor MI 48109 USA

ISBN: (纸本)9781479981311

B-mode ultrasound tongue imaging is widely used in the speech production field. However, efficient interpretation is in a great need for the tongue image sequences. Inspired by the recent success of unsupervised deep learning approach, we explore unsupervised convolutional network architecture for the feature extraction in the ultrasound tongue image, which can be helpful for the clinical linguist and phonetics. By quantitative comparison between different unsupervised feature extraction approaches, the denoising convolutional autoencoder (DCAE)-based method outperforms the other feature extraction methods on the reconstruction task and the 2010 silent speech interface challenge. A Word Error Rate of 6.17% is obtained with DCAE, compared to the state-of-the-art value of 6.45% using Discrete cosine transform as the feature extractor. Our codes are available at https://***/DeePBluE666/Source-code1.

关键词： B-mode ultrasound tongue imaging unsupervised learning feature extraction convolutional autoencoder denoising convolutional autoencoder

来源：评论

学校读者我要写书评

暂无评论

Nonnegative Constrained Graph Based Canonical Correlation Analysis for Multi-view Feature Learning

引用

NEURAL processing LETTERS 2019年第2期50卷 1215-1240页

作者： Tan, Huibin Zhang, Xiang Lan, Long Huang, Xuhui Luo, Zhigang Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Inst Quantum Informat State Key Lab High Performance Comp Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Coll Comp Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Dept Comp Sci Coll Comp Changsha Hunan Peoples R China

Understanding and analyzing multi-view data is a fundamental research topic of feature learning for a wide range of practical applications such as image classification. Canonical correlation analysis (CCA) is a popular unsupervised method of analyzing multi-view data, which captures common subspace of two groups of variable sets by maximizing the correlations between them. However, traditional CCA ignores the underlying geometric structure within dataset, which shows great power in describing data distribution, and thus fails in some tasks such as classification. To handle this limitation, this paper proposes an improved CCA variant of Nonnegative Constrained Graph regularized CCA (NCGCCA). Specifically, we improve CCA to NCGCCA with the following two contributions. Firstly, we develop a nonnegative constrained graph based self-representation to explore the underlying group-wise structure within dataset. Secondly, based on the proposed informative representation, we offer a graph embedding schema to incorporate the underlying structure into CCA. Experiments of image classification on four face datasets including Yale, ORL, UMIST, and YaleB demonstrate the efficacy of NCGCCA compared with existing baseline CCA methods.

关键词： Canonical correlation analysis Face recognition Sparse projection Cross-view correlation

来源：评论

学校读者我要写书评

暂无评论

Dithen: A Computation-as-a-Service Cloud Platform for Large-Scale Multimedia processing

引用

IEEE TRANSACTIONS ON CLOUD COMPUTING 2019年第2期7卷 509-523页

作者： Doyle, Joseph Giotsas, Vasileios Anam, Mohammad Ashraful Andreopoulos, Yiannis Dithen 843 Finchley Rd London NW11 8NA England Univ East London Univ Way London E16 2RD England UCL Elect & Elect Engn Dept Roberts Bldg Torrington Pl London WC1E 7JE England Univ Calif San Diego Ctr Appl Internet Data Anal CAIDA UCSD-SDSC9500 Gilman Dr La Jolla CA 92093 USA

We present Dithen, a novel computation-as-a-service (CaaS) cloud platform specifically tailored to the parallel execution of large-scale multimedia tasks. Dithen handles the upload/download of both multimedia data and executable items, the assignment of compute units to multimedia workloads, and the reactive control of the available compute units to minimize the cloud infrastructure cost under deadline-abiding execution. Dithen combines three key properties: (i) the reactive assignment of individual multimedia tasks to available computing units according to availability and predetermined time-to-completion constraints;(ii) optimal resource estimation based on Kalman-filter estimates;(iii) the use of additive increase multiplicative decrease (AIMD) algorithms (famous for being the resource management in the transport control protocol) for the control of the number of units servicing workloads. The deployment of Dithen over Amazon EC2 spot instances is shown to be capable of processing more than 80,000 video transcoding, face detection and image processing tasks (equivalent to the processing of more than 116 GB of compressed data) for less than $1 in billing cost from EC2. Moreover, the proposed AIMD-based control mechanism, in conjunction with the Kalman estimates, is shown to provide for more than 27 percent reduction in EC2 spot instance cost against methods based on reactive resource estimation. Finally, Dithen is shown to offer a 38 to 500 percent reduction of the billing cost against the current state-of-the-art in CaaS platforms on Amazon EC2 (Amazon Lambda and Amazon Autoscale). A baseline version of Dithen is currently available at *** under the "AutoScale" option.

关键词： Computation-as-a-service big data multimedia computing cloud computing Amazon EC2 spot instances

来源：评论

学校读者我要写书评

暂无评论

Detecting and Characterising Small-Scale Brightenings in Solar Imaging Data

引用

SOLAR PHYSICS 2021年第9期296卷 140-140页

作者： Humphries, Llyr Dafydd Morgan, Huw Kuridze, David Aberystwyth Univ Fac Business & Phys Sci Aberystwyth SY23 3FL Ceredigion Wales

Observations of small-scale brightenings in the low solar atmosphere can provide valuable constraints on possible heating and heat transport mechanisms. We present a method for the detection and analysis of brightenings, and demonstrate its application to time-series imagery of the Interface Region Imaging Spectrograph (IRIS) in the extreme ultraviolet (EUV). The method is based on spatio-temporal band-pass filtering, adaptive thresholding and centroid tracking, and records an event's spatial position, duration, total brightness and maximum brightness. Spatial area, brightness, and position are also recorded as functions of time throughout the event's lifetime. Detected brightenings can fragment, or merge, over time - thus the number of distinct regions constituting a brightening event is recorded over time, and the maximum number of regions recorded as N-frag, which is a simple measure of an event's coherence or spatial complexity. A test is made on a synthetic datacube composed of a static background based on IRIS data, Poisson noise and approximate to 10(4) randomly-distributed, moving, small-scale Gaussian brightenings. Maximum brightness, total brightness, area, and duration follow power-law distributions, and the results show the range over which the method can successfully extract information. The test shows that the recorded maximum brightness of an event is a reliable measure for the brightest and most accurately detected events, with an error of 6%. Event area, duration and speed are generally underestimated by around 15% and have an uncertainty of 20-30%. The total brightness is underestimated by 30%, and has an uncertainty of 30%. Applying this detection method to real IRIS quiet-sun data spanning 19 minutes over a 54.40 '' x55.23 '' field of view (FOV) yields 2997 detections, 1340 of these detections either remain un-fragmented or fragment to two distinct regions at least once during their lifetime (N-frag <= 2), equating to an event density of 3.96x10(

关键词： methods: data analysis methods: observational Sun: activity Sun: transition region Techniques: image processing

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：