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271-280 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：

Incremental feedback learning mechanism for highly efficient automatic image segmentation with feature coupling

Incremental feedback learning mechanism for highly efficient...

引用

2021 IEEE international conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2021

作者： Bhagwat, Manisha Gupta, Gyanendra Ambhaikar, Asha Kalinga University Dept.of CSE Raipur India

ISBN: (纸本)9781665435215

Segmentation of images is a pre-requisite for all modern high efficiency image processing system. In order to perform this task, various application specific algorithms are designed and deployed by image processing experts. These systems work on a context-specific mode, wherein all segmentation outputs are restricted by context of images for which the system is trained. In order to deploy these systems to other domains, complex tuning and optimization operations are needed. This reduces applicability of these system models for real time use cases, where general purpose segmentation methods are needed. These use cases include but are not limited to, scene classification, satellite image classification, yield prediction, traffic detection, etc. Moreover, general purpose image segmentation models work effectively only under a pre-set types of application scenarios, and need to be constantly trained in order to improve their applicability. Retraining these systems increases computational costs, and requires large training and testing delays. In order to remove these drawbacks, in this text an incremental feedback learning mechanism with feature coupling is proposed. The proposed model uses a wide variety of image segmentation methods that analyze colour, texture shape information;and map it with relevant image features. These features are traced along with segmentation quality metrics like peak signal to noise ratio (PSNR), figure of merit (FOM), minimum mean squared error (MMSE), and probabilistic random index (PRI) in order to evaluate the best segmentation algorithm. These features are classified using an ensemble classification model for selection of the most efficient segmentation method that maximizes PSNR, PRI while minimizing MMSE. Parametric evaluation suggests that the proposed model is able to improve segmentation accuracy by 8%, and reduce false alarm rate by 15% when compared with standard automatic segmentation models. © 2021 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

New Generative image Model for Variational Autoencoders Based on Counts Partition 7

New Generative Image Model for Variational Autoencoders Base...

引用

7th IEEE international conference on Information Technology and Nanotechnology, ITNT 2021

作者： Antsiperov, Viacheslav Kotelnikov Institute of Radioengineering and Electronics of Russian Academy of Sciences Signal Processing and Telecommunication Lab Moscow Russia

ISBN: (纸本)9781665432177

The article substantiates a generative image model based on a sample of random counts and its representation using compressed (coded) lattice partitioning. The basics of the model proposed is a concept of the ideal image. To avoid the problems with cumbersome descriptions, the ideal image is reduced to a sample of counts of a fixed (controlled) size. It is shown that the corresponding statistical description can be factorized into the product of the distributions of individual counts, which fits well with naive Bayesian algorithms and other machine learning approaches. Guided by this association in the image and likeness of the well-known K-means algorithm, the method of iterative partitioning - maximization of counts was synthesized. The main goal of the method is to calculate the maximum likelihood parameters of sample probability distribution and to use these parameters as a code for some intermediate representation of the input data. The method specific feature is the use of lattice neighbourhood trick for partitioning counts, that allows to control both the computation time and some characteristics of the resulting code. The final of the article is devoted to the algorithmic details of the proposed partition-maximization method are considered and several iterations related characteristics, including the convergence property, convergence criterion and asymptotic efficiency of the resulting estimates are discussed. Most of those characteristics are illustrated by the results of numerical simulations. © 2021 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Research on image enhancement algorithm based on deep neural network algorithm

Research on image enhancement algorithm based on deep neural...

引用

2021 international conference on Artificial Intelligence and Information Technology, ICAIIT 2021

作者： Lin, Qiang wen Li, Liu mei Academic affaires office Guangzhou College of Commerce Guangdong Guangzhou511363 China

image denoising and enhancement technology plays an important role in remote sensor image processing. Due to the low brightness, signal-to-noise ratio and contrast of image processing, the traditional remote sensor is limited in obtaining object information. Based on the principle of biological segmentation algorithm, neural network algorithm technology can carry the advantages of image evaluation algorithms such as PSNR, IFC and SSIM, through the end-to-end training of nonlinear infinite approximation, and carry out the research of image fitting low light level image enhancement and denoising. On this basis, the effectiveness of the research results is evaluated. The results show that compared with the traditional remote sensor imaging technology, the PSNR value of the image constructed by the depth neural network algorithm is significantly improved by about 15.2401, the IFC value is improved by about 0.4523, and the SSIM value is improved by about 0.4500, which improves the low light level imaging quality to a higher extent, and provides excellent technical guidance for the remote sensor to obtain the object information at night. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

DeCloud GAN: An advanced Generative Adversarial Network for Removing Cloud Cover in Optical Remote Sensing imagery 4

DeCloud GAN: An Advanced Generative Adversarial Network for ...

引用

4th international conference on Computational Intelligence and Intelligent Systems (CIIS)

作者： Bhambani, Krisha Takalikar, Mukta Pune Inst Comp Technol Pune Maharashtra India

ISBN: (纸本)9781450385930

Optical Remote Sensing imagery has several applications in monitoring the states of natural and man-made features around the globe. However, due to clouds and other climatic conditions, information extracted from the imagery retrieved is very limited. Deep learning has often been used in several image processing and remote sensing tasks. In this work, we propose the usage of generative adversarial networks to remove clouds and other climatic interference from high-resolution remote sensing imagery. We have trained and tested upon the Remote sensing image Cloud rEmoving dataset (RICE). The novel network(DeCloud GAN) we propose, makes use of residual UNets and pixel shuffle layers in the generator, which yield high quality cloudless satellite images. We have tested 4 methods for comparison, and have found that DeCloudGAN achieves the best performance on two main metrics, peak signal to noise ratio (PSNR) and structural similarity index (SSIM), to measure similarity in visual perception of the produced and target images.

关键词： Generative Adversarial Networks Deep Learning Optical imagery Remote Sensing image generation

来源：评论

学校读者我要写书评

暂无评论

image Segmentation Techniques and Optimization algorithms for Lung Cancer Detection 1

引用

1st international conference on Advances in signal processing and Communication Engineering (ICASPACE)

作者： Sucharitha, B. Devi, Damisetti Savitri Sushmitha, Jakku MJCET ECED Hyderabad Telangana India MJCET ECE Hyderabad Telangana India

ISBN: (数字)9789811955501

ISBN: (纸本)9789811955525;9789811955501;9789811955495

The most frequent malignancy is lung cancer and it has the greatest fatality rate among all types of cancer. Early discovery and treatment of the condition can minimize the mortality rate and probability. Other imaging methods are not as good as CT. CT scan images are visually interpreted and it can be a time-consuming and errorprone endeavor, delaying lung cancer identification Lung cancer was diagnosed using chest X-ray films but using these films, the cancer is not classified into various and accuracy obtained is not acceptable. The main goal is to develop an automated method for detecting lung cancer in scans. image preprocessing methods such as median filtering are proposed, followed by segmentation of the lung region of interest using mathematical morphological operations and optimization algorithms such as Particle Swarm Optimization, k-means clustering and Inertia Weighted Particle Swarm Optimization. Out of all, the algorithms k-means clustering out performed with the high (Brindha et al. in J Chem Pharm Sci, 2016) gave a highest accuracy of 90% than the other methods which has only 89.05% accuracy.

关键词： Lung cancer Malignant Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

A Compendious Analysis of Advances in HE Methods for Contrast Enhancement 2nd

A Compendious Analysis of Advances in HE Methods for Contras...

引用

2nd international conference on VLSI, Communication and signal processing, VCAS 2019

作者： Vijayalakshmi, D. Nath, Malaya Kumar National Institute of Technology Puducherry Karaikal India

ISBN: (纸本)9789811568398

image enhancement is a crucial pre-processing technique for image processing applications such as satellite images, medical images, and aerial surveillance systems. The image enhancement aims to produce visual content of the image in more pleasing and more suitable for machine vision applications. Enhancement of image can be improved by either increasing the contrast of the image with a low dynamic range or by highlighting the prominent details of the image. In this paper, a comprehensive analysis of bi-histogram and two-dimensional histogram equalization-based contrast enhancement techniques is performed. The performance of the various algorithms has been validated through three different databases and various performance measures. From the compendious analysis, it can be interpreted that modeling an algorithm with lower absolute mean brightness error (AMBE) and higher contrast values can render a better-enhanced image. From the qualitative and quantitative analysis, edge enhancing bi-histogram equalization using guided image filter outperforms the other contrast enhancement techniques. © 2021, Springer Nature Singapore Pte Ltd.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Lightweight Multi-scale Attentional Network for Single image Dehazing

Lightweight Multi-scale Attentional Network for Single Image...

引用

international conference on image processing, Computer Vision and Machine Learning (ICICML)

作者： Zong, Ping Li, Jinjiang Hua, Zhen Shandong Technol & Business Univ Sch Informat & Elect Engn Yantai Peoples R China Shandong Technol & Business Univ Sch Comp Sci & Technol Yantai Peoples R China

ISBN: (纸本)9781665464680

Neural network-based image dehazing algorithms have obtained extensive research results. However, haze retention is still present in the results for complex outdoor images. Designing complicated networks may be improved, yet they consist of a tremendous number of parameters, which causes slow inference and requires a more demanding computer environment for *** network globally adopts a U-Net-like structure and employs two improved modules ARM and SAM based on the attention mechanism to implement multi-scale feature extraction and fusion. Our proposed network combines the high and low level semantics in diverse scale feature images while raising the focus on diverse haze concentration regions. Experimental results reveal that our network can get improved visual results in RESIDE-SOTS (Outdoor) and NTIRE2021 NH-HAZE image Dehazing Challenge datasets in comparison with other SOTA methods and attains higher Peak signal to Noise Ratio and Structural Similarity Index.

关键词： image dehazing multi-scale feature extraction and fusion

来源：评论

学校读者我要写书评

暂无评论

RGB image Guided Depth Hole-Filling Using Bidirectional Attention Mechanism 1

引用

17th international conference on Intelligent Information Hiding and Multimedia signal processing (IIH-MSP) / 14th international conference on Frontiers of Information Technology, Applications and Tools (FITAT)

作者： Chen, Anran Zhao, Yao Lin, Chunyu Beijing Jiaotong Univ Inst Informat Sci Beijing Key Lab Adv Informat Sci & Network Beijing 100044 Peoples R China

ISBN: (数字)9789811910531

ISBN: (纸本)9789811910531;9789811910524

Depth maps obtained by commercial depth sensors are more likely to have missing values due to the occlusion effect, low-reflection objects, etc. Filling holes of depth maps is an important way to meet the demands of depth related computer vision tasks. In this paper, we propose an efficient end-to-end network that takes RGB image and mask of the hole to jointly guide the depth hole-filling. Previous algorithms indistinguishably treat valid pixels and holes, resulting in inaccurate depth values prediction and blurred boundaries. Nevertheless, the proposed algorithm uses the bidirectional attention mechanism which takes the surrounding valid values as the auxiliary information to focus on the process of depth hole-filling from edge to center. The proposed method achieves competitive performance on existing public datasets.

关键词： Bidirectional attention mechanism Depth map Hole-filling RGB guided

来源：评论

学校读者我要写书评

暂无评论

Sparse noise minimization in image classification using Genetic Algorithm and DenseNet 5

Sparse noise minimization in image classification using Gene...

引用

5th IEEE Annual international conference on Information Communications Technology and Society (ICTAS)

作者： Mienye, Ibomoiye Domor Ainah, Priye Kenneth Emmanuel, Ikiomoye Douglas Esenogho, Ebenezer Univ Johannesburg Dept Elect & Elect Engn Johannesburg South Africa Niger Delta Univ Dept Elect & Elect Engn Wilberforce Isl Nigeria Univ Salford Sch Comp Sci & Engn Salford Lancs England Univ Johannesburg Ctr Telecommun Dept Elect & Elect Engn Johannesburg South Africa

ISBN: (纸本)9781728180816

Noise handling is a critical aspect of image processing, which can significantly affect the accuracy of classification and recognition algorithms. In this paper, we propose a technique for improved noise handling in sparse input feature maps where the noise signal is also sparse. The signal-noise relationship is formulated as an optimization problem which is solved by a genetic algorithm. The genetic algorithm is applied to optimize the setting of a non-convexity parameter which yields a more accurate image sparse matrix. The resulting feature map is then classified using a densely connected convolutional network (DenseNet). Lung computed tomography images were used for the experiments. The proposed approach achieves better performance when the classification results are compared with a case in which the input signal has not been denoised using the proposed approach.

关键词： ADMM DenseNet genetic algorithm lung cancer sparse noise

来源：评论

学校读者我要写书评

暂无评论

Deformation Field Component Attention Fusion for Coarse-to-Fine Medical image Registration Network 9

Deformation Field Component Attention Fusion for Coarse-to-F...

引用

9th international conference on Intelligent Computing and signal processing, ICSP 2024

作者： Zhang, Chi Zhao, Haifeng Liu, Deyin School of Computer Science and Technology Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui University Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Hefei China School of Artificial Intelligence Anhui University Hefei China

ISBN: (纸本)9798350376548

In recent years, deep learning-based medical image registration algorithms have demonstrated notable achievements in improving registration accuracy and speed. However, these algorithms have not explored the potential benefits of utilizing different networks to generate distinct deformation fields, which can then be integrated to produce a final deformation field. In this paper, we propose deformation field component attention fusion for coarse-to-fine medical image registration. Specifically, the registration process is divided into multiple stages, which generate different deformation fields that focus on capturing deformations of varying degrees. To ensure the effective integration of multiple deformation fields, we propose the Deformation Field Component Attention Fusion Module. This module separates the deformation field into three axial displacement components and performs independent attention fusion for the different axial displacement components. Through comparative experiments and ablation studies, we demonstrate the effectiveness of the proposed method. © 2024 IEEE.

关键词： image registration

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 << < 24 25 26 27 28 29 30 31 32 33 > >>

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：