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

2,744 篇 会议
162 篇 期刊文献
19 册 图书

馆藏范围

2,925 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,735 篇 工学
- 1,168 篇 计算机科学与技术...
- 743 篇 电气工程
- 435 篇 软件工程
- 332 篇 信息与通信工程
- 225 篇 控制科学与工程
- 221 篇 生物医学工程（可授...
- 129 篇 光学工程
- 109 篇 仪器科学与技术
- 95 篇 电子科学与技术（可...
- 76 篇 机械工程
- 60 篇 生物工程
- 33 篇 测绘科学与技术
- 27 篇 材料科学与工程（可...
- 23 篇 交通运输工程
- 22 篇 化学工程与技术
- 17 篇 安全科学与工程
- 14 篇 动力工程及工程热...
468 篇 理学
- 213 篇 数学
- 182 篇 物理学
- 85 篇 生物学
- 59 篇 统计学（可授理学、...
- 53 篇 系统科学
- 27 篇 地球物理学
- 19 篇 化学
401 篇 医学
- 268 篇 临床医学
- 124 篇 特种医学
- 46 篇 基础医学(可授医学...
- 25 篇 药学(可授医学、理...
186 篇 管理学
- 145 篇 管理科学与工程(可...
- 48 篇 图书情报与档案管...
14 篇 法学
13 篇 军事学
11 篇 农学
10 篇 艺术学
4 篇 经济学
2 篇 教育学

主题

302 篇 computational mo...
262 篇 image processing
247 篇 signal processin...
225 篇 image segmentati...
209 篇 signal processin...
195 篇 feature extracti...
173 篇 image reconstruc...
136 篇 computational in...
127 篇 image coding
123 篇 deep learning
115 篇 artificial intel...
108 篇 training
86 篇 computational ef...
86 篇 image edge detec...
83 篇 computational co...
82 篇 visualization
81 篇 neural networks
79 篇 computer vision
78 篇 accuracy
76 篇 image analysis

机构

14 篇 signal and image...
11 篇 obuda univ john ...
7 篇 john von neumann...
6 篇 department of co...
5 篇 shanghai jiao to...
5 篇 nanyang technol ...
5 篇 univ chinese aca...
4 篇 centre for multi...
4 篇 univ chinese aca...
4 篇 xidian univ sch ...
4 篇 xidian univ natl...
4 篇 tsinghua univ de...
4 篇 huazhong univ sc...
4 篇 obuda university...
4 篇 wuhan univ techn...
4 篇 keio univ dept e...
4 篇 obuda univ docto...
4 篇 univ memphis dep...
4 篇 department of el...
3 篇 department of el...

作者

9 篇 chen yen-wei
6 篇 gabbouj moncef
6 篇 mendel jerry m.
6 篇 kozlovszky miklo...
6 篇 tefas anastasios
6 篇 egiazarian karen
6 篇 richard m. leahy
5 篇 pitas ioannis
5 篇 hamid r. tizhoos...
5 篇 fang liu
5 篇 zhaokui li
4 篇 xiangbin shi
4 篇 molnar bela
4 篇 r.m. leahy
4 篇 li xin
4 篇 tao yang
4 篇 yuan xin
4 篇 jerry m. mendel
4 篇 miklos kozlovszk...
4 篇 loncaric sven

语言

2,912 篇 英文
9 篇 中文
4 篇 其他

检索条件"任意字段=IEEE Symposium on Computational Intelligence in Image and Signal Processing"

共 2925 条记录，以下是471-480 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：

Subjective assessment of super-resolution 4K video using paired comparison

Subjective assessment of super-resolution 4K video using pai...

引用

International symposium on Intelligent signal processing and Communication Systems (ISPACS)

作者： Sugie, Masaki Gohshi, Seiichi Takeshita, Hirohisa Mori, Chinatsu Kogakuin Univ Dept Informat Tokyo Japan

ISBN: (纸本)9781479961207

4K television (TV) sets are available in the retail market and some are advertised as featuring a super-resolution (SR) function. In particular, most rely on super-resolution image reconstruction (SRR) to provide high-resolution images. Recently, another SR technology that uses nonlinear signal processing (NLSP) and can work in real time has been proposed. A visual performance of the technology needs to be demonstrated subjectively because the performance of the video equipment is determined subjectively by the end user. The subjective performance of these two SR functions has not been verified. Here, subjective assessments comparing SRR and NLSP and a simple extension by the Lanczos filter (without SR) were conducted. 4K video equipment and 4K experimental videos were used. The assessments combined Scheffe's paired comparison test and BT. 500, the International Telecommunication Union-Radiocommunication Sector's methodology for the subjective assessment of the quality of TV pictures. The assessment results were statistically analyzed, and the results indicated that NLSP demonstrated superior resolution.

关键词： high definition television image reconstruction image resolution video signal processing 4K television sets International Telecommunication Union-Radiocommunication Sector Lanczos filter Scheffe paired comparison test nonlinear signal processing super-resolution 4K video super-resolution function super-resolution image reconstruction video equipment HDTV image quality image resolution Observers signal resolution Video equipment video equipment high-definition television image resolution signal resolution Video signal processing image reconstruction Paired Comparisons image quality Observers Television super-resolution SAVANNAH RIVER OPERATIONS OFFICE Strontium

来源：评论

学校读者我要写书评

暂无评论

Edge saliency based on Biological inspiration for object edge extraction under low illumination 11

Edge saliency based on Biological inspiration for object edg...

引用

11th International symposium on computational intelligence and Design (ISCID)

作者： Deng, Qicao Zhang, Liping Dou, Yiwen Wu, Jincenzi Liu, Tao AnHui Polytechn Univ Sch Mech & Automot Engn Wuhu Peoples R China AnHui Polytechn Univ Sch Comp & Informat Wuhu Peoples R China Deakin Univ Fac Sci Engn & Built Environm Geelong Vic Australia

ISBN: (纸本)9781538685273

Objects edge extraction under low illumination image is helpful to enhance the scotopic vision of human visual system. At present, the traditional edge detection algorithm can not find the important edge information under the low illumination image directly. Due to tackle this problem, an optimized the visual saliency model by using the biological heuristic intelligent algorithm is proposed. It is convenient to obtain edge information of low illuminance image. First of all, after obtaining low illumination image, the visual focus is extracted from optimized visual saliency model at three channel and multi-scale level. Then those edge saliency focuses are determined by normalization and merging strategy. In this way, it lays the foundation for the posterior procedures of visual processing. Experimental results show that the proposed algorithm can accurately locate and extract the edge of the objects under normal illumination and low illumination, and it also has the characteristics of high noise resistance.

关键词： Low Illumination image Edge Saliency Firefly Population Entropy

来源：评论

学校读者我要写书评

暂无评论

A Framework for image Classification for an Efficient Dictionary Based Face Recognition System

A Framework for Image Classification for an Efficient Dictio...

引用

ieee International Conference on computational intelligence and Computing Research (ICCIC)

作者： Shahidhabanu, S. Maheswari, N. Geethalakshmi, M. Rajalakshmi Engn Coll Madras Tamil Nadu India VIT Univ Madras Tamil Nadu India VIT Univ SCSE Madras Tamil Nadu India

ISBN: (纸本)9781479915941;9781479915958

The digital multimedia image processing and its functionality of Face recognition have become more flexible. In a variety of digital forensic applications such as source identification, content analysis and authentication, it is necessary to recognize the source with training set. The proposed red length based image classification algorithm is to perform face recognition based on class specific dictionaries and to train the samples from / to each class. The class specific dictionaries are formed with some fixed number of color components. Then compares the test image with the threshold specific class and extract the minimal training set stored in the dictionary. The time taken for the image comparison leads to efficient dictionary based facial recognition which can be then used as proof of evidence towards image forensics.

关键词： image classification Face recognition image forensics

来源：评论

学校读者我要写书评

暂无评论

An Algebraic Expert System with Neural Network Concepts for Cyber, Big Data and Data Migration 19

An Algebraic Expert System with Neural Network Concepts for ...

引用

19th ieee International symposium on signal processing and Information Technology (ISSPIT)

作者： Rudd-Orthner, Richard N. M. Mihaylova, Lyudmilla Univ Sheffield Dept Automat Control & Syst Engn Sheffield S Yorkshire England MASS KSA Riyadh Saudi Arabia

ISBN: (纸本)9781728153414

This paper describes a machine assistance approach to grading decisions for values that might be missing or need validation, using a mathematical algebraic form of an Expert System, instead of the traditional textual or logic forms and builds a neural network computational graph structure. This Experts System approach is also structured into a neural network like format of: input, hidden and output layers that provide a structured approach to the knowledge-base organization, this provides a useful abstraction for reuse for data migration applications in big data, Cyber and relational databases. The approach is further enhanced with a Bayesian probability tree approach to grade the confidences of value probabilities, instead of the traditional grading of the rule probabilities, and estimates the most probable value in light of all evidence presented. This is ground work for a Machine Learning (ML) experts system approach in a form that is closer to a Neural Network node structure.

关键词： Artificial intelligence Knowledgebase Expert Systems Neural Network Information Assurance

来源：评论

学校读者我要写书评

暂无评论

Double Linear Correlation using DCT and Its Application to Forward and Reverse Matching

Double Linear Correlation using DCT and Its Application to F...

引用

8th International symposium on image and signal processing and Analysis (ISPA)

作者： Ito, Izumi Egiazarian, Karen Tokyo Inst Technol Tokyo 1528551 Japan Tampere Univ Technol Dept Signal Proc Tampere Finland

ISBN: (纸本)9789531841948;9789531841870

We propose a method of double linear correlation, which enables simultaneous calculation of the linear correlation between a sequence and a template and of the linear correlation between the sequence and the reversed template. Using the symmetric property of the discrete cosine transform (DCT) basis, we need to neither expand sequences symmetrically nor reverse the template. Proper zero-padding in the spatial domain before and after the sequences is considered to isolate the two linear correlations. The proposed method requires DCT types 1 and 2. The computational complexity of the proposed method is lower than that using fast Fourier transform.

关键词： correlation methods discrete cosine transforms pattern matching

来源：评论

学校读者我要写书评

暂无评论

Exploring Transfer Function Nonlinearity in Echo State Networks

Exploring Transfer Function Nonlinearity in Echo State Netwo...

引用

ieee symposium on computational intelligence for Security and Defense Applications (CISDA)

作者： Goudarzi, Alireza Shabani, Alireza Stefanovic, Darko Univ New Mexico Dept Comp Sci Albuquerque NM 87131 USA Google Inc Venice CA 90291 USA Univ New Mexico Ctr Biomed Engn Albuquerque NM 87131 USA

ISBN: (纸本)9781467375573

Supralinear and sublinear pre-synaptic and dendritic integration is considered to be responsible for nonlinear computation power of biological neurons, emphasizing the role of nonlinear integration as opposed to nonlinear output thresholding. How, why, and to what degree the transfer function nonlinearity helps biologically inspired neural network models is not fully understood. Here, we study these questions in the context of echo state networks (ESN). ESN is a simple neural network architecture in which a fixed recurrent network is driven with an input signal, and the output is generated by a readout layer from the measurements of the network states. ESN architecture enjoys efficient training and good performance on certain signal-processing tasks, such as system identification and time series prediction. ESN performance has been analyzed with respect to the connectivity pattern in the network structure and the input bias. However, the effects of the transfer function in the network have not been studied systematically. Here, we use an approach tanh on the Taylor expansion of a frequently used transfer function, the hyperbolic tangent function, to systematically study the effect of increasing nonlinearity of the transfer function on the memory, nonlinear capacity, and signal processing performance of ESN. Interestingly, we find that a quadratic approximation is enough to capture the computational power of ESN with tanh function. The results of this study apply to both software and hardware implementation of ESN.

关键词： Electronic Serial Number TRANSFER FUNCTIONS hyperbolic tangent nonlinearity Taylor series NETWORK STRUCTURE input signal signal processing Quadratic Approximation computational power Neural Networks (Computer)

来源：评论

学校读者我要写书评

暂无评论

Electroencephalographic Method Using Fast Fourier Transform Overlap processing for Recognition of Right- or Left-handed Elbow Flexion Motor imagery

Electroencephalographic Method Using Fast Fourier Transform ...

引用

ieee symposium on computational intelligence in Brain Computer Interfaces (CIBCI)

作者： Hiroyasu, Tomoyuki Ohkubo, Yuuki Yamamoto, Utako Doshisha Univ Kyoto 1-3 Tatara Miyakodani Kyotanabe Kyoto 6100394 Japan Doshisha Univ Grad Sch Kyoto Kyotanabe Kyoto 6100394 Japan

ISBN: (纸本)9781479945436

Recently, systems using motor imagery (MI) have been developed as practical examples of brain-computer interface (BCI). Electroencephalography (EEG) was used to generate an electroencephalogram of elbow flexion. In addition, a method was proposed to extract the feature values that would enable the recognition right- or left-handed elbow flexion MI. In the proposed method, fast Fourier transform overlap processing was used to determine the time period required to extract feature values. In this study, the following two experiments were performed. 1) the recognition of right- or left-handed elbow flexion by analyzing only the MI time period and 2) recognition of the right- or left-handed when the MI time period was presumed. In the first experiment, right- or left-handed elbow flexion MI was processed for 20 subjects using support vector machine and the proposed method was used to extract the feature values. In the second experiment, the presumed MI time was determined using the channels in which the highest accuracy was obtained in the first experiment, and then, right- or left-handed recognition was processed for the time period presumed. In the first experiment, the recognition accuracy of the proposed method was superior to that of the previous method in 15 of 20 the subjects. In the second experiment, the mean accuracy was 7.2%. Therefore, the recognition accuracy can be improved by improving the MI detection method.

关键词： biomechanics electroencephalography fast Fourier transforms feature extraction image recognition medical image processing support vector machines BCI EEG brain-computer interface electroencephalographic method fast Fourier transform overlap processing feature extration left-handed elbow flexion motor imagery recognition right-handed elbow flexion motor imagery recognition support vector machine time period Accuracy Bandwidth Elbow Electroencephalography Feature extraction Rhythm Scalp Electroencephalography Support Vector Network Feature extraction Fast Fourier transform elbow flexion Brain-Computer Interfaces Medical image processing image recognition time periods Rhythms Scalp Recognition (Psychology) Elbow Bandwidth Biomechanics

来源：评论

学校读者我要写书评

暂无评论

image Captioning using Deep Learning: Text Augmentation by Paraphrasing via Backtranslation

Image Captioning using Deep Learning: Text Augmentation by P...

引用

ieee symposium Series on computational intelligence (ieee SSCI)

作者： Turkerud, Ingrid Ravn Mengshoel, Ole Jakob NTNU Dept Comp Sci Trondheim Norway

ISBN: (纸本)9781728190488

image captioning, an exciting but challenging area of research at the intersection of natural language processing and computer vision, has recently seen dramatic progress. Much of the progress has been due to advances in machine learning and the availability of suitable data sets consisting of images, each with multiple captions. However, there has been little research on the impact of varying the number of captions on the quality of image captioning results. In particular, does it improve image captioning performance if we increase the number of captions in a dataset by augmenting the existing captions with paraphrases created using backtranslation? In this paper, we address this question and make the following three main contributions. First, we present a novel method of adding captions to a dataset by means of paraphrasing via backtranslation. Backtranslation amounts, in our case, to translating an English caption to a French counterpart which is then translated back to English. Typically, this results in the backtranslated English caption being different from the original English caption. Such backtranslated English captions can thus be used to augment the original dataset. Second, using our method, we generate paraphrases for the seminal MS COCO image captioning dataset. Our paraphrase dataset consists of around 490 000 paraphrased captions that are different from the original captions in MS COCO. Third, in image captioning experiments with deep learning models, we use datasets augmented with backtranslated paraphrases. We study the extent to which augmenting image captioning training datasets with paraphrases improves image captioning models' performance, and report promising results. Code and data are publicly available.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

ICA in image processing: A Survey

ICA in Image Processing: A Survey

引用

2015 ieee International Conference on computational intelligence & Communication Technology (CICT 2015)

作者： Goel, Swati Verma, Akhilesh Goel, Savita Juneja, Komal AKGEC Dept CSE Ghaziabad India IIT Delhi CSC New Delhi India

ISBN: (纸本)9781479960224

Source separation is a problem in which signals are mixed together. It is becoming a tedious task to recuperate original components signal from the signal mixture. Blind Source Separation (BSS) is suggested as a key to the problem aiming at finding the linear representation in such a way that the components are statistically (stochastically) independent. Independent Component Analysis (ICA) is an approach that attained a wider attention and a growing significance in a diverse range of research fields for accomplishing Blind Source Separation. This paper includes preface of ICA, its variants and their list of applications in brief.

关键词： ICA image model Filter bank Global features Texture segmentation

来源：评论

学校读者我要写书评

暂无评论

Fast content-based image retrieval using quasi-gabor filter and reduction of image feature dimension 5

Fast content-based image retrieval using quasi-gabor filter ...

引用

5th ieee Southwest symposium on image Analysis and Interpretation

作者： Park, M Jin, JS Wilson, LS Univ New S Wales Sch Engn & Comp Sci Kensington NSW 2033 Australia

ISBN: (纸本)0769515371

This paper introduces a new approach to content based image retrieval by texture. There are three problems to solve: high computational time, handling high dimension data, and comparing images consistent with human perception. To decrease the computational time, we present a new strategy to extract an image feature with high retrieval accuracy. We also propose how to reduce the image feature dimension using the reward-punishment algorithm, so any robust indexing methods can be used. BY weighting the extracted image features, a system may perceive the image consistently with human perception.

关键词： Content based retrieval Database systems Digital images Gabor filters image databases image retrieval Information retrieval Physics Spatial databases Tellurium

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293页 << < 44 45 46 47 48 49 50 51 52 53 > >>

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：