检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

4,423 篇 会议
232 篇 期刊文献
55 册 图书
10 篇 学位论文
3 篇 资讯

馆藏范围

4,723 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

2,622 篇 工学
- 1,500 篇 计算机科学与技术...
- 885 篇 电气工程
- 773 篇 软件工程
- 463 篇 信息与通信工程
- 331 篇 控制科学与工程
- 292 篇 生物医学工程（可授...
- 223 篇 光学工程
- 210 篇 机械工程
- 162 篇 电子科学与技术（可...
- 143 篇 仪器科学与技术
- 126 篇 生物工程
- 89 篇 材料科学与工程（可...
- 68 篇 测绘科学与技术
- 58 篇 化学工程与技术
- 32 篇 土木工程
- 27 篇 建筑学
- 25 篇 力学（可授工学、理...
1,484 篇 理学
- 925 篇 物理学
- 656 篇 数学
- 431 篇 统计学（可授理学、...
- 228 篇 系统科学
- 139 篇 生物学
- 64 篇 化学
759 篇 医学
- 594 篇 临床医学
- 222 篇 特种医学
- 78 篇 基础医学(可授医学...
- 44 篇 药学(可授医学、理...
214 篇 管理学
- 119 篇 管理科学与工程(可...
- 103 篇 图书情报与档案管...
- 25 篇 工商管理
24 篇 农学
17 篇 法学
13 篇 教育学
12 篇 经济学
10 篇 艺术学
9 篇 文学
2 篇 军事学

主题

548 篇 image processing
461 篇 image segmentati...
390 篇 stochastic proce...
365 篇 statistical anal...
259 篇 feature extracti...
231 篇 bayesian methods
224 篇 image reconstruc...
188 篇 signal processin...
187 篇 image analysis
141 篇 pixel
135 篇 image restoratio...
109 篇 statistics
106 篇 pattern recognit...
105 篇 image edge detec...
103 篇 hidden markov mo...
103 篇 image coding
99 篇 noise reduction
96 篇 testing
96 篇 robustness
95 篇 histograms

机构

10 篇 school of electr...
8 篇 indian statistic...
7 篇 univ penn dept r...
7 篇 department of el...
7 篇 department of el...
7 篇 univ waterloo de...
7 篇 univ michigan de...
6 篇 nanyang technol ...
6 篇 smart computer v...
6 篇 computer vision ...
5 篇 georgia inst tec...
5 篇 microsoft resear...
5 篇 carnegie mellon ...
5 篇 signal and image...
5 篇 peng cheng lab p...
4 篇 google res mount...
4 篇 texas a&m univ.
4 篇 department of sy...
4 篇 ivan kozhedub kh...
4 篇 tokyo metropolit...

作者

9 篇 landman bennett ...
8 篇 vorapoj patanavi...
8 篇 dougherty er
8 篇 h. krim
7 篇 yannick berthoum...
7 篇 a.s. willsky
7 篇 sang hwa lee
6 篇 astola jaakko t.
6 篇 prince jerry l.
6 篇 umapada pal
6 篇 alexander wong
6 篇 udupa jk
6 篇 nam ik cho
6 篇 w. pieczynski
6 篇 fessler jeffrey ...
6 篇 w.c. karl
6 篇 pesquet jean-chr...
6 篇 pal umapada
6 篇 jong-il park
6 篇 pieczynski w

语言

4,631 篇 英文
49 篇 其他
31 篇 中文
13 篇 土耳其文
1 篇 西班牙文
1 篇 法文
1 篇 俄文

检索条件"任意字段=Conference on Statistical and Stochastic Methods for Image Processing"

共 4723 条记录，以下是801-810 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

An image Steganalysis Model Combined with the Directionality of Residuals 6th

An Image Steganalysis Model Combined with the Directionality...

引用

6th International conference on Artificial Intelligence and Security,ICAIS 2020

作者： Jin, Zhujun Li, Hao Yang, Yu Lin, Jialin School of Cyberspace Security Beijing University of Posts and Telecommunications Beijing100876 China College of New Media Beijing Institute of Graphic Communication Beijing102600 China

ISBN: (纸本)9789811580857

In recent years, many steganalysis methods using convolutional neural networks have been proposed. In the existing steganalysis networks, in order to enhance steganalysis noise and reduce the impact of image content, the high-pass filter is applied to extract residuals. However, the residual is usually directly input into a network for feature extraction, without considering further processing to enhance the statistical feature extraction of the subsequent network. Furthermore, the processing of convolutional layer in a network can be viewed as horizontal and vertical scanning maps, and the form of directions is simple. In this paper, to enrich directional features, the directionality of residuals is incorporated into the learning of network. Before feature extraction, residuals are rearranged in the direction of minor-diagonal. In addition, local binary pattern is applied to the residual map to obtain the correlation between each element in residual map and its multi-directional adjacent elements. Three spatial steganography algorithms, WOW, HUGO and S-UNIWARD, are selected in the simulation. The simulation results show that the incorporation of residual directionality into convolutional neural network can improve the steganalysis performance of the network. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

image CORRECTION IN EMISSION TOMOGRAPHY USING DEEP CONVOLUTION NEURAL NETWORK 44

IMAGE CORRECTION IN EMISSION TOMOGRAPHY USING DEEP CONVOLUTI...

引用

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

作者： Suzuki, Tomohiro Kudo, Hiroyuki Univ Tsukuba Grad Sch Syst & Informat Engn Dept Comp Sci Tennoudai 1-1-1 Tsukuba Ibaraki 3058573 Japan

ISBN: (纸本)9781479981311

We propose a new approach using Deep Convolution Neural Network (DCNN) to correct for image degradations due to statistical noise and photon attenuation in Emission Tomography (ET). The proposed approach first reconstructs an image by the standard Filtered Backprojection (FBP) without correcting for the degradations followed by inputting the degraded image into DCNN to obtain an improved image. We consider two different scenarios. The first scenario inputs an ET image only into DCNN, whereas the second scenario inputs a pair of degraded ET image and CT/MRI image to improve accuracy of the correction. The simulation result demonstrates that both the scenarios can improve image quality compared to the FBP without correction, and, in particular, accuracy of the second scenario is comparable to that of the standard iterative reconstruction such as Maximum Likelihood Expectation Maximization (MLEM) and Ordered-Subsets EM (OSEM) methods. The proposed method is able to output an image in very short time, because it does not rely on iterative computations.

关键词： Convolution neural network emission tomography image reconstruction attenuation correction

来源：评论

学校读者我要写书评

暂无评论

Gaussian noise removal algorithm using statistical method 8

Gaussian noise removal algorithm using statistical method

引用

8th IEEE International conference on Communication and Signal processing, ICCSP 2019

作者： Halder, Amiya Samaddar, Debadri St. Thomas College of Engineering and Technology Kolkatta India

ISBN: (纸本)9781538675953

In this paper, a new efficient Gaussian noise removal algorithm is proposed that removes the Gaussian noises from the noisy images. This proposed method depends on statistical parameters like local standard deviation and local mean. It preserves the fine details of images along with the image restoration. In proposed method, a smoothing factor is introduced which determines the level of restoration. This factor is automatically calculated using standard deviation. From various experimental results, it is confirmed that the proposed method yields better results than the different existing methods. © 2019 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

SPI-OPTIMIZER: AN INTEGRAL-SEPARATED PI CONTROLLER FOR stochastic OPTIMIZATION 26

SPI-OPTIMIZER: AN INTEGRAL-SEPARATED PI CONTROLLER FOR STOCH...

引用

26th IEEE International conference on image processing (ICIP)

作者： Wang, Dan Ji, Mengqi Wang, Yong Wang, Haoqian Fang, Lu Tsinghua Univ Tsinghua Berkeley Shenzhen Inst Beijing Peoples R China Shenzhen Inst Future Media Technol Shenzhen Peoples R China Hong Kong Univ Sci & Technol Hong Kong Peoples R China

ISBN: (纸本)9781538662496

To overcome the oscillation problem in the classical momentum-based optimizer, recent work associates it with the proportional-integral (PI) controller, and artificially adds D term producing a PID controller. It suppresses oscillation with the sacrifice of introducing extra hyper-parameter. In this paper, we analyze that the fluctuation problem relates to the lag effect of the integral (I) term, and propose SPI-Optimizer, an integral-Separated PI controller based optimizer WITHOUT introducing extra hyper-parameter. It separates momentum term adaptively when the inconsistency of current and historical gradient direction occurs. Extensive experiments demonstrate that SPI-Optimizer generalizes well on popular network architectures to eliminate the oscillation, and owns competitive performance with faster convergence speed (up to 40% epochs reduction ratio) and more accurate classification result on MNIST, CIFAR10, and CIFAR100 (up to 27.5% error reduction ratio) than state-of-the-art methods.

关键词： Method of moments Oscillators Convergence PI control Optimization Network architecture Training

来源：评论

学校读者我要写书评

暂无评论

Hardware-in-the-Loop End-to-End Optimization of Camera image processing Pipelines

Hardware-in-the-Loop End-to-End Optimization of Camera Image...

引用

conference on Computer Vision and Pattern Recognition (CVPR)

作者： Ali Mosleh Avinash Sharma Emmanuel Onzon Fahim Mannan Nicolas Robidoux Felix Heide Algolux Princeton University

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Commodity imaging systems rely on hardware image signal processing (ISP) pipelines. These low-level pipelines consist of a sequence of processing blocks that, depending on their hyperparameters, reconstruct a color image from RAW sensor measurements. Hardware ISP hyperparameters have a complex interaction with the output image, and therefore with the downstream application ingesting these images. Traditionally, ISPs are manually tuned in isolation by imaging experts without an end-to-end objective. Very recently, ISPs have been optimized with 1st-order methods that require differentiable approximations of the hardware ISP. Departing from such approximations, we present a hardware-in-the-loop method that directly optimizes hardware image processing pipelines for end-to-end domain-specific losses by solving a nonlinear multi-objective optimization problem with a novel 0th-order stochastic solver directly interfaced with the hardware ISP. We validate the proposed method with recent hardware ISPs and 2D object detection, segmentation, and human viewing as end-to-end downstream tasks. For automotive 2D object detection, the proposed method outperforms manual expert tuning by 30% mean average precision (mAP) and recent methods using ISP approximations by 18% mAP.

关键词： Hardware Task analysis Pipelines Measurement Cameras Optimization methods

来源：评论

学校读者我要写书评

暂无评论

Absolute 3d Pose Estimation and Length Measurement of Severely Deformed Fish from Monocular Videos in Longline Fishing

Absolute 3d Pose Estimation and Length Measurement of Severe...

引用

IEEE International conference on Acoustics, Speech and Signal processing

作者： Jie Mei Jenq-Neng Hwang Suzanne Romain Craig Rose Braden Moore Kelsey Magrane University of Washington Seattle WA USA National Oceanic and Atmospheric Administration USA

Monocular absolute 3D fish pose estimation allows for efficient fish length measurement in the longline fisheries, where fishes are under severe deformation during the catching process. This task is challenging since it requires locating absolute 3D fish keypoints based on a short monocular video clip. Unlike related works, which either require expensive 3D ground-truth data and/or multiple-view images to provide depth information, or are limited to rigid objects, we propose a novel frame-based method to estimate the absolute 3D fish pose and fish length from a single-view 2D segmentation mask. We first introduce a relative 3D fish template. By minimizing an objective function, our method systematically estimates the relative 3D pose of the target fish and fish 2D keypoints in the image. Finally, with a closed-form solution, the relative 3D fish pose can help locate absolute 3D keypoints, resulting in the frame-based absolute fish length measurement, which is further refined based on the statistical temporal inference for the optimal fish length measurement from the video clip. Our experiments show that this method can accurately estimate the absolute 3D fish pose and further measure the absolute length, even outperforming the state-of-the-art multi-view method.

关键词： Three-dimensional displays Closed-form solutions Pose estimation Optimization methods Length measurement Signal processing Fish

来源：评论

学校读者我要写书评

暂无评论

image processing and Classification Method Appropriate for Extensible Mobile Applications 10

Image Processing and Classification Method Appropriate for E...

引用

10th International conference on Information, Intelligence, Systems and Applications (IISA)

作者： Petrellis, Nikos Univ Thessaly Comp Sci & Engn Gen Dept Larisa Greece

ISBN: (纸本)9781728149592

The image processing technique described in this paper can be used for the classification of photographs that display an object of interest. Spots on the object having distinct color surrounded by a potential halo are segmented. The gray level, area and the number of the spots can determine the class of the object displayed in the photograph. The color histograms of the regions of interest are expected to have similar form in different photographs belonging to the same class. Instead of employing complicated pattern matching algorithms simple features are used including the position and the peaks of the lobes. Plant or skin disease diagnosis are indicative applications that can benefit from the proposed method. High speed classification is achieved with good accuracy in the cases where the proposed methods have been employed. However, their main advantage is the simplicity that allows extensibility since new classes can be supported after a draft statistical processing of a small number of photographs.

关键词： image processing pattern matching plant disease skin disorder segmentation classification smart phone apps

来源：评论

学校读者我要写书评

暂无评论

Study on Stocks Based on Big Data methods and Computer Programs

Study on Stocks Based on Big Data Methods and Computer Progr...

引用

image processing, Electronics and Computers (IPEC), Asia-Pacific conference on

作者： Cheng Wang Hailei Zou Juncheng Yin Applied Math Dept China Jiliang Univ. Hang Zhou City China

ISBN: (数字)9781728160672

ISBN: (纸本)9781728160689

Recently big data is a hot topic in many fields. Here we use distributed algorithms to treat big data in Chinese stock market. First the two stock indexes (Shanghai Composite and Shenzhen Composite indexes) from 1990-2019 are collected. Then the data are divided to several subsets and are analyzed separately via computer programs. Finally the results for every subset are combined due to distributed algorithms theory. In addition to big data scheme, we adopt stochastic processes theory and moment equations methods.

关键词： Distributed algorithm Big data Lèvy processes Chinese stock index Moment estimations Lè vy processes big data distributed algorithms stocks Computers

来源：评论

学校读者我要写书评

暂无评论

Don't Take the Easy Way Out: Ensemble Based methods for Avoiding Known Dataset Biases 9

Don't Take the Easy Way Out: Ensemble Based Methods for Avoi...

引用

conference on Empirical methods in Natural Language processing / 9th International Joint conference on Natural Language processing (EMNLP-IJCNLP)

作者： Clark, Christopher Yatskar, Mark Zettlemoyer, Luke Univ Washington Paul G Allen Sch CSE Seattle WA 98195 USA Allen Inst Artificial Intelligence Seattle WA USA

ISBN: (纸本)9781950737901

State-of-the-art models often make use of superficial patterns in the data that do not generalize well to out-of-domain or adversarial settings. For example, textual entailment models often learn that particular key words imply entailment, irrespective of context, and visual question answering models learn to predict prototypical answers, without considering evidence in the image. In this paper, we show that if we have prior knowledge of such biases, we can train a model to be more robust to domain shift. Our method has two stages: we (1) train a naive model that makes predictions exclusively based on dataset biases, and (2) train a robust model as part of an ensemble with the naive one in order to encourage it to focus on other patterns in the data that are more likely to generalize. Experiments on five datasets with out-of-domain test sets show significantly improved robustness in all settings, including a 12 point gain on a changing priors visual question answering dataset and a 9 point gain on an adversarial question answering test set.

关键词： statistical tests

来源：评论

学校读者我要写书评

暂无评论

Experimental Modeling the Flow of Character Recognition Results in Video Stream for Document Recognition 11

Experimental Modeling the Flow of Character Recognition Resu...

引用

11th International conference on Machine Vision (ICMV)

作者： Andreeva, Elena Arlazarov, Vladimir V. Slavin, Oleg Janiszewski, Igor Russian Acad Sci Inst Syst Anal Fed Res Ctr Comp Sci & Control Moscow Russia Smart Engines Ltd Moscow Russia Moscow Inst Phys & Technol Moscow Russia

ISBN: (数字)9781510627499

ISBN: (纸本)9781510627499

This paper considers problems regarding the development of stochastic models consistent with the results of character image recognition in video stream. Assumptions about their structure and properties are formulated for the constructed models. The description of the model components defines the Dirichlet distribution and its generalizations. The parameters of these distributions are determined using statistical estimation methods. The Akaike information criterion is used to rank models. The verification of the agreement of the proposed theoretical distributions to the sample data is carried out.

关键词： stochastic model video stream the character recognition Dirichlet distribution Akaike criterion goodness-of-fit Anderson-Darling tests

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共473页 << < 77 78 79 80 81 82 83 84 85 86 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：