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

4,146 篇 会议
71 篇 期刊文献
10 册 图书

馆藏范围

4,227 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,936 篇 工学
- 2,152 篇 计算机科学与技术...
- 1,311 篇 软件工程
- 717 篇 信息与通信工程
- 481 篇 电气工程
- 451 篇 光学工程
- 398 篇 生物医学工程（可授...
- 349 篇 生物工程
- 287 篇 控制科学与工程
- 203 篇 电子科学与技术（可...
- 188 篇 机械工程
- 188 篇 仪器科学与技术
- 128 篇 测绘科学与技术
- 120 篇 化学工程与技术
- 111 篇 材料科学与工程（可...
- 99 篇 土木工程
- 89 篇 建筑学
- 82 篇 航空宇航科学与技...
- 80 篇 环境科学与工程（可...
- 71 篇 安全科学与工程
- 68 篇 网络空间安全
1,309 篇 理学
- 521 篇 数学
- 511 篇 物理学
- 383 篇 生物学
- 172 篇 统计学（可授理学、...
- 139 篇 化学
487 篇 管理学
- 285 篇 图书情报与档案管...
- 223 篇 管理科学与工程(可...
443 篇 医学
- 364 篇 临床医学
- 187 篇 基础医学(可授医学...
- 134 篇 药学(可授医学、理...
71 篇 农学
64 篇 法学
25 篇 经济学
23 篇 教育学
12 篇 艺术学
10 篇 军事学
7 篇 文学
1 篇 哲学

主题

282 篇 image reconstruc...
238 篇 image segmentati...
214 篇 feature extracti...
188 篇 deep learning
180 篇 data mining
171 篇 image processing
133 篇 image classifica...
126 篇 training
118 篇 convolutional ne...
110 篇 accuracy
106 篇 data models
92 篇 image recognitio...
88 篇 image enhancemen...
81 篇 remote sensing
73 篇 image analysis
72 篇 computer vision
68 篇 image color anal...
65 篇 machine learning
63 篇 computational mo...
61 篇 visualization

机构

13 篇 chitkara univers...
12 篇 chitkara univ in...
6 篇 school of comput...
6 篇 chitkara univers...
6 篇 school of data a...
5 篇 vishwakarma inst...
5 篇 graphic era deem...
5 篇 uttaranchal univ...
4 篇 beijing institut...
4 篇 china academy of...
4 篇 chennai
4 篇 wuhan univ sch r...
4 篇 center for earth...
4 篇 univ chinese aca...
4 篇 computer science...
4 篇 geomatics engine...
4 篇 cccc big data te...
4 篇 university of ch...
4 篇 sun yat sen univ...
4 篇 waseda universit...

作者

8 篇 li jonathan
7 篇 wang cheng
7 篇 zhang wei
6 篇 sharma neha
6 篇 li li
6 篇 wang wei
6 篇 wang yan
6 篇 li yan
6 篇 chen yen-wei
5 篇 wang jing
5 篇 gupta rupesh
5 篇 b. solaiman
5 篇 m.s. bouhlel
5 篇 rueckert daniel
5 篇 zhang jun
4 篇 vibhute amol d.
4 篇 zhang lei
4 篇 gill kanwarparta...
4 篇 xie bin
4 篇 chen chen

语言

3,824 篇 英文
380 篇 其他
35 篇 中文
2 篇 法文
1 篇 泰文

检索条件"任意字段=2nd Conference on Image Reconstruction from Incomplete Data"

共 4227 条记录，以下是651-660 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：

Multimodal medical image fusion using guided filter and curvelet transform 2

Multimodal medical image fusion using guided filter and curv...

引用

2nd IEEE International conference on New Technologies of Information and Communication, NTIC 2022

作者： Hedifa, Dida Fella, Charif Abderrazak, Benchabane Department of Electronics and Telecommunications Ouargla Algeria Electronics and Telecommunications Department Algeria

ISBN: (纸本)9781665489744

The results of resonance magnetic imaging and computerized tomography of the target organ provide complementary information about this organ that helps the radiologist in the diagnosis process. Despite the information provided by these two techniques, the radiologist needs a single sensor result containing the information of the CT and MRI image for better diagnosis of the disease. image fusion is the process of merging complementary data of several sensors into a unique image. In this study, we propose a new approach for fusing CT and MRI of brain images using a guided filter and curvelet transform. Our method is based mainly on three basic steps, which are as following: Firstly, Extracted detail layers from each input image adopting a guided filter. Secondly, based on removing the blurred images from the input images, clearer images are obtained. Finally, the images are combined using the curvelet transform. The proposed method has been compared to effective fusion methods. Through the obtained qualitatively and quantitatively results, the proposed method showed a good result compared to other methods of fusion. © 2022 IEEE.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

Research on image Stegnography using based on Suduko matrix and LSB Value with multi-level encryption 2

Research on Image Stegnography using based on Suduko matrix ...

引用

2nd IEEE Mysore Sub Section International conference, MysuruCon 2022

作者： Rathour, Navjot Rawat, Poonam Uttaranchal University Dehradun India

ISBN: (数字)9781665497909

ISBN: (纸本)9781665497916

In order to conceal data in such a manner that is invisible to a viewer, digital steganography makes use of the host signal. A complete reproduction of the actual picture is possible with discrete wavelet transform which translate integers to numbers. So, we put forth a method that incorporates the signal bit stream into the LSBs of the integer wavelets of a true picture. Additionally, the method performs a preprocessing phase on the cover image to correct saturation pixel components and retrieve the encrypted messages without losing it. Due to our growing dependence on digital media, novel techniques of safeguarding it from unauthorised use are urgently needed. Encryption is one of the methods that has been used in real-world applications for a very long time. The capability to exchange data between people in a way which prohibits someone else from accessing it is the fundamental service which cryptography provides. The presented model's high transparency, even with big message sizes, was demonstrated by experimental findings. © 2022 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

image Segmentation Algorithm of Ischemic Stroke based on Wavelet Pooling Neural Network 2

Image Segmentation Algorithm of Ischemic Stroke based on Wav...

引用

2nd IEEE International conference on Signal, Information and data Processing, ICSIDP 2024

作者： Zhu, Huiyuan Zhai, Yao Wu, Jinghe Lu, Chuwei Zhang, Xianchao Li, Ruide Beijing Institute of Technology School of Cyberspace Science and Technology Beijing China College of Medicine Jiaxing University Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems Department of Nursing Jiaxing China Beijing Institute of Technology School of Information and Electronics Beijing China Aviation Industry Corporation of China Avic Xi' An Flight Automatic Control Research Institute Xi'an China Jiaxing University Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems Jiaxing China

ISBN: (纸本)9798331515669

Ischemic stroke is a high-risk brain disease that causes disability or death in adults worldwide. Rapid diagnosis and treatment, as well as segmentation of ischemic lesions from stroke medical images so that doctors can evaluate and develop treatment plans, are crucial to reducing brain damage. Currently, doctors' manual segmentation of lesions is time-consuming and labor-intensive and prone to missed or misdiagnosed diagnoses, delaying the best time for treatment. A well-trained neural network is considered as an effective aid for image segmentation tasks. However, in the traditional neural network down-sampling process, the pooling layer loses feature information, and the lost information significantly impacts the edge regions. While for medical images, edge regions are crucial features in the segmentation process. Therefore, to address the above issues, in this paper we improve upon the existing stroke lesion segmentation algorithm U-net, we design a segmentation network based on wavelet pooling and attention mechanisms. The network was tested on ISLES 2018 and ISLES 2022 datasets, and the Dice coefficient improved by 2.13% and 1.93% compared to baseline network, respectively. © 2024 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Colourization of Black and White images using Convolutional Autoencoder

Colourization of Black and White Images using Convolutional ...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International conference on

作者： Mukta Jukaria Riya Kavidayal Priyanka Bhatt Tabeer Rizvi Graphic Era Hill University Haldwani India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

image colourization, the process of adding colour to grayscale images, remains a significant challenge in computer vision with diverse applications in digital media. This paper presents the development and evaluation of a convolutional autoencoder model designed for automatic image colourization. The methodology involves converting grayscale images into the LAB colour space, where the ‘L’ channel is used as input to predict the ‘A’ and ‘B’ channels. The model architecture integrates convolutional layers for feature extraction and upsampling layers for image reconstruction. The Adam optimizer is employed to minimize the Mean Absolute Error (MAE) during training. Utilizing a landscape image dataset and incorporating data augmentation techniques, the model achieved an accuracy of 85.34%, demonstrating effective colour preservation and detail enhancement. This approach automates the colourization process with high efficiency and provides valuable insights for practical applications in digital media.

关键词： Training Accuracy image color analysis Computer architecture Media Gray-scale Feature extraction data models Optimization image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Siamese-Prototypical Network with data Augmentation Pre-training for Few-shot Medical image Classification 2

Siamese-Prototypical Network with Data Augmentation Pre-trai...

引用

2nd International conference on Frontiers of Electronics, Information and Computation Technologies, ICFEICT 2022

作者： Yan, Jin Feng, Kaiyuan Zhao, Hongyu Sheng, Kai Chinatelecom e Cloud Company Cloud Network Operation Department Beijing China School of Electronic Engineering Xidian University Xi'an China Academy of Adfvance Interdisciplinary Research Xidian University Xi'an China

ISBN: (数字)9781665454766

ISBN: (纸本)9781665454766

The main challenge for few-shot medical image classification is that we have a limited number of labeled samples that can be used for training. This may lead to biases in the representation of prototype features, thus affecting the classification performance. In order to solve these problems, a Siamese-Prototypical network with data augmentation pre-training algorithm is proposed for few-shot medical image classification. In this framework, we extend the scarce medical dataset by data augmentation, so that the feature extractor has stronger generalization ability. This feature extractor is then transferred to the meta-learning phase. In the meta-learning phase, we employ a Siamese-Prototypical network to obtain a prototype with higher accuracy. In addition, the supervision information from the support label is used to calibrate the prototype generated from the features of support set, and then use it to predict the samples of support set in the same measure. Our model optimizes three losses, two of the additional losses are dedicated to learning more representative prototypes for more accurate predictions. Experiments on three benchmark medical image classification datasets testify that the proposed method can yield superior accuracy for few-shot medical image classification. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Dual-Power Approach for Skin Disease Classification Using ResNet-50 and SVM 2

A Dual-Power Approach for Skin Disease Classification Using ...

引用

2nd IEEE Global conference on Communications and Information Technologies, GCCIT 2024

作者： Kaur, Jashanpreet Rani, Shalli Singh, Gurpreet Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura140401 India

ISBN: (纸本)9798350388916

In this reasearch, we propose a reliable skin disease detection system by integrating a deep learning model, ResNet50, with a Support Vector Machine (SVM) classifier. Using the recommended methodology, six types of skin diseases that is Acne, Carcinoma, Eczema, Keratosis, Milia, and Rosacea should be ***-50 is used for feature extraction;its deep design allows it to extract fine details from pictures of skin lesions. An SVM classifier which is renowned for its effectiveness in binary classification problems is then fed the gathered information. To determine the efficacy of the model, training and assessment are conducted on a skin disease dataset that spans many epochs. The model achieves a training accuracy of 99.55% and a validation accuracy of 97.90% after 85 epochs, demonstrating high generalization and learning capacity based on experimental data.. To further support the robustness of the model, the validation loss dropped from 0.4037 at 5 epochs to 0.0865 by 85 epochs. Owing to its reliable performance in training and validation, dermatologists may utilize the model in clinical settings for the early and accurate detection of skin problems. The integration of SVM with ResNet-50 has demonstrated efficacy, yielding a scalable and dependable solution for the categorization of skin conditions. © 2024 IEEE.

关键词： Deep learning Medical image analysis ResNet-50 Skin disease classification SVM classifier

来源：评论

学校读者我要写书评

暂无评论

Intersection over Union based analysis of image detection/segmentation using CNN model 2

Intersection over Union based analysis of Image detection/se...

引用

2nd International conference on Power, Control and Computing Technologies, ICPC2T 2022

作者： Gajjar, Amitkumar N Jethva, Jigneshkumar Madhav University Dept of EC Pindwara India

ISBN: (纸本)9781665458580

Neural networks are capable of learning high-dimensional hierarchical structures of objects from huge quantities Deep-learning systems can learn to recognize photographs based on a large amount of training data. Artificial intelligence has this as one of its features. Deep-learning algorithms for picture interpretation may be divided into two groups. SegNet, U-Net, and SharpMask are examples of fully convolutional methods that use an encoder-decoder architecture. Region-based methods, on the other hand, use a convolutional neural network (CNNs) stack to extract features, such as Mask-RCNN, PSP Net and DeepLab. When the networks are trained on a large enough number of annotated datasets, region-based methods beat for most image segmentation tasks, fully convolutional techniques are used. We designed and incorporated deep-learning techniques based on Mask-RCNN to detect 2D images while creating a segmentation for each mask item in this paper. © 2022 IEEE.

关键词： image segmentation Visualization Neural networks Semantics Power control Training data Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Multi-Source Remote Sensing image Registration Method Based on Nonlinear Scale Space and Phase Congruency 2

Multi-Source Remote Sensing Image Registration Method Based ...

引用

2nd IEEE International conference on Signal, Information and data Processing, ICSIDP 2024

作者： Chen, Yuejuan Li, Xianglei Huang, Pingping Tan, Weixian Li, Xiujuan Yin, Bo Inner Mongolia University of Technology Mongolia Key Laboratory of Radar Technology and Application College of Information Engineering Hohhot China Inner Mongolia University of Technology Mongolia Key Laboratory of Radar Technology and Application College of Resources and Environmental Engineering Hohhot China

ISBN: (纸本)9798331515669

Due to differences in sensor characteristics, imaging conditions, and time among multi-source remote sensing images, nonlinear changes in image radiance intensity occur, increasing the difficulty of image registration. Existing techniques often face challenges in the robustness and accuracy of feature matching when addressing these nonlinear radiance variations. To solve this problem, this paper proposes a phase congruency remote sensing image registration method based on nonlinear scale space. This method constructs a nonlinear scale space of the image using an improved anisotropic diffusion filter, effectively suppressing noise while preserving the edges and detailed features of the image. It calculates the edge strength and corner strength of the image at different scales using a phase congruency model and extracts feature points from the edge strength map and corner strength map. Multi-scale, multi-direction descriptors are constructed using the response values generated by the Log-Gabor filter to enhance the robustness of feature extraction, thereby achieving precise registration of multi-source remote sensing images. Experimental results show that this method significantly suppresses image noise and nonlinear radiance differences, and outperforms traditional algorithms and other improved registration algorithms regarding the number of correctly matched point pairs and robustness. © 2024 IEEE.

关键词： Gabor filters

来源：评论

学校读者我要写书评

暂无评论

Classification of Gastrointestinal Diseases Using Deep Transfer Learning 2

Classification of Gastrointestinal Diseases Using Deep Trans...

引用

2nd International conference on Intelligent Cybernetics Technology and Applications (ICICyTA) - Cybernetic Technology for Better Future of Human Life

作者： Ni Wong, Wan Wong, Yit Khee Chan, Weng Howe Univ Teknol Malaysia Fac Comp Johor Baharu Malaysia

ISBN: (纸本)9798350399134

As a part of the digestive system, gastrointestinal (GI) tract is importantly involved in digestive activities by breaking down food as consumed into compounds and absorbing nutrients from them. Digestive-related problems such as bloating, constipation, and diarrhea, should be treated seriously as they could be signs and symptoms of chronic diseases such as cancer. Therefore, endoscope is used for GI examination to allow video or image capture of the GI tract. With the availability of GI endoscopic image data, data scientists and doctors can work together to analyze patient records to best understand GI diseases. This study is aimed to implement deep transfer learning for classifying GI diseases. Initially, the GI dataset with 3 classes and 5542 endoscopic images is collected from two sources - Kvasir and Hyper-Kvasir. After exploratory data analysis, pre-processing steps are taken to clean, standardize, and transform the data. data splitting and data augmentation techniques are then conducted to avoid overfitting during model development. In this study, pretrained ResNet50 which is a convolutional neural network with 50 layers, is proposed for the classification task. To evaluate the model, performance metrics and benchmarking are applied. Based on the obtained results, the proposed model demonstrates high stability with consistent scores. As compared with ResNet18 and ResNet34 models, it also achieves higher accuracy, precision, recall, and F1-score with 94% on average.

关键词： image classification gastrointestinal diseases deep transfer learning convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Fusion Method of Power Customer data Model and Power Grid Asset Equipment Business data Model 2

Fusion Method of Power Customer Data Model and Power Grid As...

引用

2nd IEEE International conference on Artificial Intelligence in Everything, AIE 2022

作者： Liang, Yingwei Peng, Zewu Xie, Hanyang Feng, Xinyao Dongguan Power Supply Bureau of Guangdong Power Grid Dongguan523000 China

ISBN: (数字)9781665474009

ISBN: (纸本)9781665474009

With the development of information technology, the amount of data and information we face has become more and more enormous. The technology that emerged at the historic moment is data mining, but traditional mining techniques show many deficiencies for incomplete information systems. Fully implement the group management of customer service data, correctly understand, meet and guide customer needs, pay attention to customer needs, formulate diversified service strategies, and provide customers with safe, reliable, efficient and convenient services. This is the power supply company to establish "good service", Good management, good image "three good service image inevitable requirements. Based on the experimental research method, this paper conducts corresponding research on the electricity customer data, and draws the following conclusions to describe the business characteristics of the electricity value contribution model to reflect the characteristics of different customer groups. The value contribution model is divided into 5 groups: high value contribution group, accounting for 2%;medium value contribution group, accounting for 10%;medium value high overdue risk group, accounting for 10%;ordinary group, accounting for 71%;Low-value contribution group, accounting for 3%. © 2022 IEEE.

关键词： data fusion

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423页 << < 62 63 64 65 66 67 68 69 70 71 > >>

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：