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

674 篇 会议
12 册 图书
5 篇 期刊文献

馆藏范围

691 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

451 篇 工学
- 322 篇 计算机科学与技术...
- 258 篇 软件工程
- 196 篇 信息与通信工程
- 138 篇 电气工程
- 84 篇 生物工程
- 72 篇 光学工程
- 64 篇 生物医学工程（可授...
- 34 篇 电子科学与技术（可...
- 24 篇 化学工程与技术
- 22 篇 控制科学与工程
- 19 篇 材料科学与工程（可...
- 17 篇 仪器科学与技术
- 13 篇 机械工程
- 12 篇 安全科学与工程
- 9 篇 动力工程及工程热...
- 8 篇 交通运输工程
- 6 篇 网络空间安全
235 篇 理学
- 110 篇 物理学
- 87 篇 生物学
- 85 篇 数学
- 22 篇 化学
- 19 篇 统计学（可授理学、...
- 9 篇 系统科学
104 篇 医学
- 102 篇 临床医学
- 23 篇 基础医学(可授医学...
- 20 篇 药学(可授医学、理...
- 6 篇 公共卫生与预防医...
72 篇 管理学
- 43 篇 图书情报与档案管...
- 31 篇 管理科学与工程(可...
6 篇 法学
6 篇 教育学
- 6 篇 教育学
5 篇 农学
2 篇 军事学

主题

98 篇 signal processin...
58 篇 image segmentati...
58 篇 image processing
54 篇 signal processin...
43 篇 conferences
41 篇 deep learning
38 篇 image enhancemen...
33 篇 image recognitio...
29 篇 feature extracti...
28 篇 training
24 篇 image edge detec...
24 篇 convolution
24 篇 visualization
24 篇 image color anal...
24 篇 image reconstruc...
22 篇 image coding
22 篇 image classifica...
20 篇 neural networks
18 篇 robustness
17 篇 object detection

机构

6 篇 school of inform...
6 篇 college of elect...
5 篇 key laboratory o...
5 篇 university of ch...
5 篇 nanyang technol ...
5 篇 school of mathem...
4 篇 shanghai jiao to...
4 篇 laboratory of be...
4 篇 school of electr...
3 篇 shanghai jiao to...
3 篇 michigan state u...
3 篇 college of mathe...
3 篇 tsinghua shenzhe...
3 篇 shanghai jiao to...
3 篇 national laborat...
2 篇 university of sc...
2 篇 school of comput...
2 篇 school of cyber ...
2 篇 school of mathem...
2 篇 huazhong univers...

作者

6 篇 wang chao
6 篇 yang chuansheng
5 篇 yang yueting
5 篇 wen bihan
5 篇 yang jian
4 篇 jian wang
4 篇 tan anhui
4 篇 anil kumar
4 篇 bo feng
4 篇 chao xu
3 篇 ravishankar saip...
3 篇 zhou jiantao
3 篇 li min
3 篇 zhai guangtao
3 篇 nguyen trong-the
3 篇 feng bo
3 篇 parthasarathy ra...
3 篇 xiaotao huang
3 篇 wang liu
3 篇 fan zhun

语言

691 篇 英文

检索条件"任意字段=2021 International Conference on Advanced Algorithms and Signal Image Processing, AASIP 2021"

共 691 条记录，以下是531-540 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：

Unveiling Anomalous Nodes Via Random Sampling and Consensus on Graphs

Unveiling Anomalous Nodes Via Random Sampling and Consensus ...

引用

IEEE international conference on Acoustics, Speech and signal processing

作者： Vassilis N. Ioannidis Dimitris Berberidis Georgios B. Giannakis University of Minnesota Minneapolis USA Carnegie Mellon University Pittsburgh USA

The present paper develops a graph-based sampling and consensus (GraphSAC) approach to effectively detect anomalous nodes in large-scale graphs. GraphSAC randomly draws sub-sets of nodes, and relies on graph-aware criteria to judiciously filter out sets contaminated by anomalous nodes, before employing a semi-supervised learning (SSL) module to estimate nominal label distributions per node. These learned nominal distributions are minimally affected by the anomalous nodes, and hence can be directly adopted for anomaly detection. The per-draw complexity grows linearly with the number of edges, which implies efficient SSL, while draws can be run in parallel, thereby ensuring scalability to large graphs. GraphSAC is tested under different anomaly generation models based on random walks, as well as contemporary adversarial attacks for graph data. Experiments with real-world graphs show-case the advantage of GraphSAC relative to state-of-the-art alternatives.

关键词： Scalability image edge detection conferences signal processing algorithms Clustering algorithms Semisupervised learning signal processing

来源：评论

学校读者我要写书评

暂无评论

Capsule Network based Super Resolution Method for Medical image Enhancement

Capsule Network based Super Resolution Method for Medical Im...

引用

IEEE international conference on signal and image processing (ICSIP)

作者： S. C. Munasingha S. Fernando Faculty of Information Technology University of Moratuwa Sri Lanka

ISBN: (纸本)9781665446006

The Convolution Neural Network (CNN) based approaches for Super-Resolution (SR) show several inherited flaws. In this paper, several Capsule Network routing mechanisms have been investigated for the current Super Resolution (SR) pipeline with a custom medical image dataset. Previously introduced, Dynamic Routing (DR) and Expectation Maximization (EM) Routing Capsule Networks are re-configured to adapt to the custom dataset. For the first time, the Inverted Dot Product-based Attention Routing mechanism is introduced for the SR. The results show that the DR-based method outperforms the other methods along with different image quality indexes. The introduced Attention Routing based approach shows better results than the popular Fast CNN for SR (FSRCNN) method and improved time performance than the DR-based method.

关键词： Training image quality Superresolution Pipelines Reconstruction algorithms Routing Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Garbage Classification System with YOLOV5 Based on image Recognition

Garbage Classification System with YOLOV5 Based on Image Rec...

引用

IEEE international conference on signal and image processing (ICSIP)

作者： Guanhao Yang Jintao Jin Qujiang Lei Yi Wang Jiangkun Zhou Zhe Sun Xiuhao Li Weijun Wang Intelligent Robot & Equipment Center Guangzhou Institute of Advanced Technology Chinese Academy of Sciences Guangzhou China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665446006

At present, the main technology of garbage identification and classification is the use of traditional machine vision algorithm or the use of sensors for screening and identification of garbage, in garbage sorting, the first accurate identification and classification of garbage is very necessary. By collecting various types of garbage pictures and building detection data sets, we adopt the garbage identification and detection algorithm based on YOLO-V5 and use data enhancement to improve the robustness of the model, to achieve fast and accurate identification of different types of garbage. Experimental results show that this method has high accuracy, short time consumption, and good robustness.

关键词： image recognition Machine vision Design methodology conferences Manipulators Robustness Data models

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Clustering of Time Series signals Using Neuromorphic Energy-Efficient Temporal Neural Networks

Unsupervised Clustering of Time Series Signals Using Neuromo...

引用

IEEE international conference on Acoustics, Speech and signal processing

作者： Shreyas Chaudhari Harideep Nair Jose M. F. Moura John Paul Shen Carnegie Mellon University

Unsupervised time series clustering is a challenging problem with diverse industrial applications such as anomaly detection, bio-wearables, etc. These applications typically involve small, low-power devices on the edge that collect and process real-time sensory signals. State-of-the-art time-series clustering methods perform some form of loss minimization that is extremely computationally intensive from the perspective of edge devices. In this work, we propose a neuromorphic approach to unsupervised time series clustering based on Temporal Neural Networks that is capable of ultra low-power, continuous online learning. We demonstrate its clustering performance on a subset of UCR Time Series Archive datasets. Our results show that the proposed approach either outperforms or performs similarly to most of the existing algorithms while being far more amenable for efficient hardware implementation. Our hardware assessment analysis shows that in 7 nm CMOS the proposed architecture, on average, consumes only about 0.005 mm~2 die area and 22 μW power and can process each signal with about 5 ns latency.

关键词： Performance evaluation Neuromorphics image edge detection Time series analysis Neural networks signal processing algorithms Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Stacked Capsule Autoencoder for Hyperspectral image Classification

Unsupervised Stacked Capsule Autoencoder for Hyperspectral I...

引用

IEEE international conference on Acoustics, Speech and signal processing

作者： Erting Pan Yong Ma Xiaoguang Mei Fan Fan Jiayi Ma School of Electronic Information Wuhan university Wuhan China Institute of Aerospace Science and Technology Wuhan university Wuhan China

Since CapsNet [1] shattered all previous records of algorithms for image recognition, the capsule's conception has attracted bright attention. It interprets an object by the geometrical arrangement of parts. We think it can be transferred to hyperspectral images. In a hyperspectral data cube, each pixel spectrum can be regarded as a continuous curve representing its inherent properties. In the spatial domain, there are various spatial distributions in different positionsand there is usually a specific structural relationship between adjacently distributed categories. Based on HSI data's aforementioned structural characteristics, combined with the stacked capsule autoencoder, we propose our model to achieve an unsupervised HSI classification. In our model, the ConvLSTM is employed to discover part capsules of HSI, and we utilize Set Transformer to encode relations among all parts and indicate object capsules. The decoders of both phases use Gaussian mixture models to reconstruct specific information. Experimental results of the Pavia Center dataset show the exceptional of our model.

关键词： image recognition Graphical models signal processing Decoding Task analysis Speech processing image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Feature Point Matching Algorithm Based on Local Relative Velocity Consensus

Feature Point Matching Algorithm Based on Local Relative Vel...

引用

6th international conference on Intelligent Computing and signal processing (ICSP)

作者： Shao Feng An Jubai Liu ZhaoXia Information Science and Technology College Dalian Maritime University Dalian China School of Software Dalian University of Foreign Languages Dalian China

ISBN: (纸本)9781665447300

Feature matching is still a crucial and challenging problem in image processing. In this paper, a novel feature matching algorithm based on local relative velocity consensus (LRVC) is proposed to find two accurate matched feature points. To remove the outliers accurately and robustly, the relative velocity between the putative matches and their corresponding neighbors are exploited. Based on the consensus of relative velocity and the consensus of neighborhood elements, the similarity of each putative matches is evaluated. With a two iteration outlier removal strategy, the feature points are matched accurately and robustly. In the experiment, VGG dataset are used to verify the accuracy and robustness of the proposed method LRVC. The matching results indicate that our method is superior to three other classic feature matching methods.

关键词： image processing signal processing algorithms signal processing Robustness

来源：评论

学校读者我要写书评

暂无评论

A Homogeneity-Based Multiscale Hyperspectral image Representation for Sparse Spectral Unmixing

A Homogeneity-Based Multiscale Hyperspectral Image Represent...

引用

IEEE international conference on Acoustics, Speech and signal processing

作者： Luciano C. Ayres Sergio J. M. de Almeida Jose C. M. Bermudez Ricardo A. Borsoi Catholic University of Pelotas Pelotas RS Brazil Federal University of Santa Catarina Florianópolis SC Brazil CNRS OCA Université Côte d’Azur Nice France

Several approaches have been proposed to solve the spectral unmixing problem in hyperspectral image analysis. Among them the use of sparse regression techniques aims to characterize the abundances in pixels based on a large library of spectral signatures known a priori. Recently, the integration of image spatial-contextual information significantly enhanced the performance of sparse unmixing. In this work, we propose a computationally efficient multiscale representation method for hyperspectral data adapted to the unmixing problem. The proposed method is based on a hierarchical extension of the SLIC oversegmentation algorithm constructed using a robust homogeneity testing. The image is subdivided into a set of spectrally homogeneous regions formed by pixels with similar characteristics (superpixels). This representation is then used to provide prior spatial regularity information for the abundances of materials present in the scene, improving the conditioning of the unmixing problem. Simulation results illustrate that the method is capable of estimating abundances with high quality and low computational cost, especially in noisy scenarios.

关键词： Simulation signal processing algorithms signal processing Spatial databases Computational efficiency Noise measurement Speech processing

来源：评论

学校读者我要写书评

暂无评论

Extending the Reverse JPEG Compatibility Attack to Double Compressed images

Extending the Reverse JPEG Compatibility Attack to Double Co...

引用

IEEE international conference on Acoustics, Speech and signal processing

作者： Jan Butora Jessica Fridrich Binghamton University Binghamton NY

The reverse JPEG compatibility attack has recently been introduced as a very accurate and universal steganalysis algorithm for JPEG images with quality 99 or 100. The limitation to these two largest qualities appears fundamental as the prior work on this topic suggests. In this paper, we provide mathematical analysis and demonstrate experimentally that this attack can be extended to double compressed images when the first compression quality is 93 or larger and the second quality equal or larger than the first quality. Comparisons with state-of-the-art deep convolutional neural networks as well as detectors built in the JPEG domain show the merit of this work.

关键词： Q-factor image coding Mathematical analysis Transform coding signal processing algorithms Detectors Reliability theory

来源：评论

学校读者我要写书评

暂无评论

Quadrotor Visual Navigation Under GPS Spoofing Attack

Quadrotor Visual Navigation Under GPS Spoofing Attack

引用

international conference on Wireless Communications, signal processing and Networking (WiSPNET)

作者： Kai Liu Yuyang Zhao Gang Wang Rui Xue School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Electronics and Information Engineering Beihang University Beijing China

This paper presents a quadrotor visual navigation system under the GPS spoofing attack. We use HACKRF to send spoofing signals to the quadrotor. The quadrotor is detected during the outer loop of the system. If the quadrotor is spoofed, the quadrotor switch to visual navigation instead of using GPS signals. In the visual navigation, the image matching technology is used to solve the actual position of the quadrotor for the positioning problem of the quadrotor. A method of information fusion based on reference map matching and motion estimation is proposed for positioning and navigation. We can extraction keypoints, get the image descriptor based on ORB algorithm and binarize them with the corresponding correct geographical coordinates as a reference map. In order to improve the search matching speed, KLT keypoint tracking algorithm is used to estimate the motion information of the quadrotor, and the rough position of auxiliary search reference map is given. Simulations and experiments show the feasibility of the proposed scheme.

关键词： Wireless communication Visualization Navigation Tracking image matching Software algorithms signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

A Color Doppler processing Engine with an Adaptive Clutter Filter for Portable Ultrasound Imaging Devices

A Color Doppler Processing Engine with an Adaptive Clutter F...

引用

IEEE international conference on Acoustics, Speech and signal processing

作者： Yi-Lin Lo Chia-Hsiang Yang Graduate Institute of Electronics Engineering National Taiwan University Taiwan National Taiwan University Taiwan

This paper presents an optimized color Doppler processing engine for portable ultrasound devices. The imaging performance is improved by the proposed adaptive clutter filter that separates the clutter from the blood signal in the frequency-eigenvalue space. The adaptive clutter filter provides high attenuation on clutter and also reserves the low-velocity blood flow. Compared to the conventional eigenvalue-based and frequency-based clutter filters, this work achieves 2.5-to-17.5dB and 1-to-12.5dB improvements, respectively, in blood-to-clutter ratio (BCR) based on an in vivo dataset with 16 images. The blood-tissue discriminator is re-arranged and integrated with the clutter filter to further enhance the imaging performance with less computational complexity. The computational complexity is reduced by 48-78% by leveraging the reduced processed area. Randomized spatial down-sampling is adopted to further reduce the processing time. An overall reduction of 60% in processing time is achieved. This work provides a promising solution to color Doppler imaging for portable ultrasound devices.

关键词： Ultrasonic imaging image color analysis Imaging Adaptive filters signal processing algorithms Filtering algorithms Doppler effect

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70页 << < 50 51 52 53 54 55 56 57 58 59 > >>

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：