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

128 篇 会议

馆藏范围

128 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

71 篇 工学
- 46 篇 计算机科学与技术...
- 26 篇 信息与通信工程
- 26 篇 软件工程
- 17 篇 光学工程
- 10 篇 电气工程
- 9 篇 电子科学与技术（可...
- 7 篇 材料科学与工程（可...
- 7 篇 生物医学工程（可授...
- 6 篇 控制科学与工程
- 5 篇 机械工程
- 5 篇 化学工程与技术
- 4 篇 仪器科学与技术
- 4 篇 交通运输工程
- 4 篇 安全科学与工程
- 4 篇 网络空间安全
- 3 篇 土木工程
- 3 篇 石油与天然气工程
- 3 篇 航空宇航科学与技...
- 3 篇 生物工程
- 2 篇 动力工程及工程热...
35 篇 理学
- 20 篇 数学
- 14 篇 物理学
- 5 篇 化学
- 5 篇 生物学
- 3 篇 统计学（可授理学、...
13 篇 管理学
- 12 篇 管理科学与工程(可...
- 3 篇 图书情报与档案管...
7 篇 医学
- 6 篇 临床医学
- 3 篇 基础医学(可授医学...
- 3 篇 公共卫生与预防医...

主题

19 篇 accuracy
18 篇 convolutional ne...
13 篇 training
12 篇 deep learning
12 篇 image processing
11 篇 signal processin...
9 篇 image segmentati...
9 篇 signal processin...
8 篇 image reconstruc...
7 篇 image enhancemen...
7 篇 real-time system...
7 篇 psnr
7 篇 feature extracti...
7 篇 image recognitio...
7 篇 image quality
6 篇 image color anal...
5 篇 support vector m...
5 篇 visualization
5 篇 machine learning...
5 篇 measurement

机构

2 篇 j.c. bose univer...
2 篇 shenyang aerospa...
2 篇 advanced semicon...
2 篇 school of comput...
2 篇 dr. d. y. patil ...
2 篇 school of comput...
2 篇 beijing - dublin...
2 篇 college of trans...
2 篇 school of electr...
2 篇 cyrinn science &...
2 篇 college of mecha...
2 篇 school of comput...
2 篇 college of compu...
2 篇 k. r. mangalam u...
2 篇 school of electr...
1 篇 department of co...
1 篇 electrical and c...
1 篇 international sc...
1 篇 gitam univ dept ...
1 篇 king mongkuts un...

作者

2 篇 yan jun
2 篇 wang changxiang
2 篇 anuradha
2 篇 ma jinshan
1 篇 teodora bakardji...
1 篇 jiang zhihao
1 篇 zhang tao
1 篇 jiayin min
1 篇 k sevitha
1 篇 kapatos c.
1 篇 bhal arpita
1 篇 celaya-padilla j...
1 篇 c surya
1 篇 chit siang soh
1 篇 valaparla david
1 篇 mitali monalisha
1 篇 ishwari kakade
1 篇 ran an
1 篇 jia zhenhong
1 篇 gole nilesh

语言

121 篇 英文
7 篇 其他

检索条件"任意字段=4th International Conference on Advanced Algorithms and Signal Image Processing, AASIP 2024"

共 128 条记录，以下是51-60 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：

Learnable upsampling bilateral grid refinement for stereo matching network 4

Learnable upsampling bilateral grid refinement for stereo ma...

引用

4th international conference on advanced algorithms and Neural Networks, AANN 2024

作者： Qiu, Wenfeng Ma, Chihao Li, Jianhua Qian, Ren Zhao, Yong College of Computer Science and Technology Guizhou University Guiyang550025 China School of Electronic and Computer Engineering Shenzhen Graduate School of Peking University Shenzhen518055 China College of Artificial Intelligence and Big data Luzhou Vocational and Technical College Sichuan Luzhou646000 China

ISBN: (纸本)9781510686106

Most existing binocular stereo matching algorithms require a trade-off between accuracy and speed, unable to achieve both simultaneously. One reason lies in the complexity and variability of scenes that stereo matching tasks must handle, where disparities in heavily textured, weakly textured, and occluded areas are often difficult to infer correctly. therefore, this paper proposes the Learnable Upsampling Bilateral Grid Refinement for Stereo Matching Network (LUGNet). through learnable bilateral grid upsampling guided by the left image, LUGNet calculates offsets for cost volume upsampling, while simultaneously leveraging the network to automatically learn interpolation weights to accommodate features of different datasets. Ultimately, LUGNet achieves error rates comparable to high-precision networks with a parameter count of 2.6M and an inference time of 58ms. © 2024 SPIE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Multi-scale target detection for airfield visual navigation of taxiing aircraft 4

Multi-scale target detection for airfield visual navigation ...

引用

4th international conference on Neural Networks, Information and Communication Engineering, NNICE 2024

作者： Luo, Qijun Chen, Jiagang Zhang, Xuerui Zhang, Tao Civil Aviation University of China Tianjin Intelligent Signal and Image Processing Experiment Tianjin300300 China

ISBN: (纸本)9798350394375

In the context of visual navigation-based civil aircraft assistance systems, the scene target scales captured by onboard cameras exhibit significant variations, and the computational power of airborne platforms is limited. To promptly and accurately identify threat targets in airborne scenic images, a lightweight multi-scale object detection algorithm based on improved YOLOv5s is proposed. Firstly, on the foundation of the Weighted Bidirectional Feature Pyramid Network (BIFPN), a Coordinate Attention (CA) mechanism is integrated to design the CA-BIFPN feature fusion network. this enhances feature representation for small targets and improves the model's learning capability for multi-scale targets. Secondly, a cross-level sub-network module is employed to lightweightly process the neck section, reducing the model's parameter count and thereby improving the overall network's detection speed. Experimental results on a self-constructed scene image dataset demonstrate that the proposed method achieves a detection frame rate of 89FPS, an increase of 5fps. the average precision mean (mAP) on the test set is 70.6%, a 3.4% improvement over the original YOLOv5s. the detection accuracy surpasses typical algorithms such as YOLOv6, YOLOv7, YOLOX, and Faster-RCNN. © 2024 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Quantification of Necrosis Cells in Heart Disease Diagnosis Using image processing 4

Quantification of Necrosis Cells in Heart Disease Diagnosis ...

引用

4th international conference on Applied Mathematics, Modeling and Computer Simulation, AMMCS 2024

作者： Poddar, Harshit Rajagopal, Sivakumar Saini, Aarushi Hemalatha, K. Vellore Institute of Technology Vellore632014 India

ISBN: (纸本)9781643685519

this study presents an inventive software application that has been developed in the LABVIEW and MATLAB environments to effectively identify hypertension and various heart irregularities, which include Sinus Bradycardia, Sinus Tachycardia, Supraventricular Tachycardia (SVT) Abnormal, Arrhythmia, and Atrial Flutter. By utilizing advanced algorithms for image processing, such as image enhancement, thresholding, mathematical morphology, and labelling, the software offers accurate identification of neurosis cells. Given the significant contribution of hypertension and heart diseases to the global health burden, with high blood pressure accounting for 54% of strokes and 47% of heart-related issues, the early and rapid detection of necrosis cells becomes imperative for improved treatment outcomes. this research provides a robust software tool that outperforms conventional methods, offering a more accurate, efficient, and accessible means of self-testing for individuals. this contribution aims to facilitate timely medical interventions and enhance health outcomes, thereby addressing the critical need for advanced diagnostic tools in cardiovascular health. © 2024 the Authors.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Phase encoding and time-frequency analysis in polar coordinates for spiking neural network design 4

Phase encoding and time-frequency analysis in polar coordina...

引用

4th international conference on advanced algorithms and Neural Networks, AANN 2024

作者： Zhang, Lei Faculty of Engineering and Applied Science University of Regina S4S 0A2 Canada

ISBN: (纸本)9781510686106

this paper presents a novel phase encoding scheme for spike trains in Spiking Neural Networks (SNNs) inspired by Fourier series and the Discrete Fourier Transform (DFT). the proposed method leverages complex exponential spiking neurons to represent frequency components, allowing for the efficient reconstruction of original time signals. We explore the time-shifting property of the Fourier transform to demonstrate how time delays in impulse signals can be encoded as phase shifts in the frequency domain. Detailed mathematical formulations and illustrative examples highlight the relationship between impulse delays and phase patterns in SNNs. the primary objective of this research is to develop a streamlined and computationally efficient SNN architecture, enhancing the training process. Future work will expand this phase encoding method to various sequence patterns, aiming to improve the performance and versatility of SNNs in neuromorphic computing for complex information processing tasks. the results indicate that this approach holds promise for advancing the field by providing a robust framework for precise signal reconstruction and efficient neural network design. © 2024 SPIE.

关键词： Discrete Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Research on high accuracy classification of temperature signals based on OFDR technology and EfficientNet 4

Research on high accuracy classification of temperature sign...

引用

4th international conference on advanced Manufacturing Technology and Electronic Information, AMTEI 2024

作者： Shang, Chuanyin Li, Peng Tong, Zhengrong Wang, Hao Li, Sibo Tianjin Key Laboratory of Thin Film Electronics and Communication Devices Engineering Research Center for Optoelectronic Devices and Communication Technology the Ministry of Education School of Integrated Circuit Science and Engineering Tianjin University of Technology Tianjin300384 China

ISBN: (数字)9781510688247

ISBN: (纸本)9781510688230

the development of machine learning is driving revolutionary changes and unprecedented opportunities across various industries. this paper introduces a new temperature monitoring method that combines the efficient deep learning model EfficientNet with Optical Frequency Domain Reflectometry (OFDR). We utilize distributed fiber-optic sensing technology based on OFDR to collect one-dimensional temperature signals under different temperature conditions, which we then transform into a two-dimensional image format suitable for machine learning processing. the dataset is subsequently trained using the EfficientNet deep learning model. the results show that the trained model achieves a high accuracy rate of 97.5% on the test dataset. this research not only demonstrates the feasibility of efficiently and accurately monitoring temperature changes but also provides new solutions and technological pathways for areas such as environmental monitoring, industrial automation, and safety systems. © 2025 SPIE.

关键词： Education and training Data modeling Performance modeling Fiber optics sensors Machine learning Matrices Fiber optics image processing Reliability signal processing

来源：评论

学校读者我要写书评

暂无评论

Investigating the Relationship between CrB Phase through image processing and Mechanical Properties of Metal 3D Printed Alloy 4

Investigating the Relationship between CrB Phase through Ima...

引用

4th IEEE international conference on Electrical, Computer, and Energy Technologies, ICECET 2024

作者： Park, Dong Yong Park, Hyeon Jeong Lee, Yoon Sun Korea Institute of Industrial Technology Advanced Mobility Components Group Daegu Korea Republic of

ISBN: (纸本)9798350395914

the relationship between the quantified CrB phase via image processing method and the mechanical properties of 3D printed SUS316L with boron was examined. Nine experimental conditions, i.e., boron content, feed rate, laser power, and scan speed, were designed by Taguchi method. the formation of CrB phase in 3D printed alloy with nine process conditions was quantified using image processing method. the image processing algorithm was based on the intensity difference between the regions of CrB phase and others. the CrB phase directly affects the mechanical properties of the 3D printed stainless steel. the quantity of CrB phase and mechanical properties depend on the processing conditions. the mechanical properties for tensile strength and micro hardness with processing conditions were measured. the same processing conditions were used for both quantification of the CrB phase and the mechanical properties test. the relationship between the quantified CrB phase and the mechanical properties was identified. As is generally known, a high amount of CrB phase deteriorates the mechanical properties of materials. therefore, optimization of the processing conditions is crucially required to achieve the desired mechanical properties. With the signal the signal-to-noise (S/N) ratio analysis, the S/N ratio results for the quantified CrB phase were compared with that for the measured mechanical properties. the comparison through S/N ratio analysis contributes to determination of the influence of the CrB phase on the mechanical properties. Also, the comparison helps in finding of the desired mechanical properties. © 2024 IEEE.

关键词： Tensile strength

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Satellite image Dehazing Using advanced Computational Techniques 4

A Novel Framework for Satellite Image Dehazing Using Advance...

引用

4th IEEE Asian conference on Innovation in Technology, ASIANCON 2024

作者： Vishwakarma, Sandeep Anuradha Punj, Deepika J.C. Bose University of Science and Technology Faridabad India Symbiosis Institute of Technology Department of Computer Science and Engineering Pune India

ISBN: (纸本)9798350354218

Satellite imagery information is used in many different ways;some of the more common ones are environmental and urban planning and disaster response. that is why haze has a highly negative impact on the quality and visibility of such images and their further usage. the following paper proposes an innovative approach to satellite images dehazing to enhance its value to professionals and researchers in the field. the ideas for the proposed method involve incorporating the use of machine learning algorithms into image enhancement procedures to adequately dehaze the images, increase image resolution, and enhance the efficiency of getting information from satellite images. Our approach involves a three-step process: seen as consisting of preprocessing, a dehazing network, and postprocessing. the preliminary processing generally includes initial enhancement operations such as histogram equalization and color stretch. the foundation of our framework is a deep learning-based dehazing network that uses CNNs, residual blocks, attention mechanisms, and GANs to dehaze and restore the images' quality. Additional operations are performed in postprocessing;they include details enlargement, the removal of noise , and color correction so as to achieve natural and quality results. We evaluate our framework using two standard satellite image datasets: the users of the mentioned services are SateHaze1k and RICE. the effectiveness of the proposed method is evaluated by means of two quality measures, namely Peak signal-to-Noise Ratio and Structural Similarity Index. Test results portray the efficiency of the proposed technique in dehazing with enhanced PSNR and SSIM values over other conventional and state-of-art works on machine learning-based dehazing methods. that is why our framework can provide the workable and scalable solution for the improvement of the satellite images' clarity that would be the beneficial for its usage in numerous applications. © 2024 IEEE.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Research on optical image quality assessment under strong light interference 4

Research on optical image quality assessment under strong li...

引用

4th international Computational Imaging conference, CITA 2024

作者： Wang, Si-Yu Feng, Yun-Song Jin, Wei Zhou, Chang-Qi Liu, Li-Ping Chen, You-Cai Key Laboratory of Infrared Low Temperature Plasma of Anhui Province National University of Defense Technology Hefei230037 China Advanced Laser Technology Laboratory of Anhui Province National University of Defense Technology Hefei230037 China State Key Laboratory of Pulsed Power Laser Technology National University of Defense Technology Hefei230037 China

ISBN: (纸本)9781510688834

In the face of technological advancements, the military domain has witnessed the emergence of diverse innovative weaponry, with optical applications in weaponry playing a pivotal role. To counteract the threat of enemy optical-guided weapons on the battlefield, it is imperative to implement countermeasures. Strong light interference stands out as a prevalent optical countermeasure technique. To achieve better strong light interference effects, we need to conduct a quantitative analysis of the strong light interference effectiveness, which is the evaluation of image quality after interference. image quality assessment is a critical process that involves comparing images using specialized methods, which can be categorized into subjective and objective evaluations. Subjective evaluation, which relies on human analysis and judgment of image similarity, is labor-intensive and requires a significant number of experts, limiting its practical application. In contrast, objective evaluation leverages computational power to execute algorithms that provide a quantitative analysis of images. this approach transforms images from an intractable entity into a form that can be systematically analyzed and quantified. this study employs MATLAB software to harness the power of five distinct algorithms: Mean Hash Algorithm, Difference Hash Algorithm, Perceptual Hash Algorithm, Histogram Cosine Similarity Algorithm, and Histogram Bias Coefficient Algorithm. these algorithms are adept at processing images and converting them into numerical representations of similarity. By employing the respective program translations of these algorithms, we can quantify the degree of image similarity, thereby facilitating a comprehensive assessment of image quality. this quantitative approach not only streamlines the evaluation process but also enhances the accuracy and reliability of the results. © 2025 SPIE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Weather Recognition Using ResNet-50 and a Novel Weather image Dataset 4

Comprehensive Weather Recognition Using ResNet-50 and a Nove...

引用

4th international signal processing, Communications and Engineering Management conference, ISPCEM 2024

作者： Wang, Jun Zhou, Yunhan Fu, Min School of Electrical and Electronics Engineering UESTC Chengdu China Cyrinn Science & Technology Ltd. Guangzhou China

ISBN: (纸本)9798331528676

Weather conditions play a crucial role in both daily human activities and industrial operations. For example, recognizing different weather patterns is critical for outdoor automation systems. With the development of AI technology, scientific researchers have trained many models which receive weather images as inputs and output the weather in these images fast and accurately. However, many existing weather recognition models are limited in scope, typically identifying only four types of weather with varying degrees of accuracy. In this study, the two key contributions of this research are: first, the creation of a custom dataset designed specifically for recognizing seven distinct weather conditions, and second, the exploration of multiple machine learning techniques to identify the most effective model for this task. By developing our own dataset, we ensure a broader representation of weather types, allowing the models to train and be tested on more diverse and realistic scenarios. We evaluate five different algorithms: Support Vector Machine (SVM), Random Forest, Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), and ResNet50. To enhance model generalization and reduce overfitting, we employ data augmentation techniques and add dropout layers in the CNN and ResNet50 architectures. through extensive experimentation, ResNet50 emerges as the best-performing model, achieving an accuracy of approximately 87% on the custom dataset. this work demonstrates the importance of creating domain-specific datasets and using a range of machine learning methods to develop accurate and reliable weather recognition models. Our approach offers a robust solution for outdoor vision systems, with potential applications in autonomous vehicles, surveillance systems, and other environments where accurate weather detection is critical for safety and performance. ©2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Block Matching and 3 Dimensions (BM3D) Filtering for image Noise Removal Using Discrete Wavelet Transformation (DWT) 4

Improving Block Matching and 3 Dimensions (BM3D) Filtering f...

引用

4th IEEE international Maghreb Meeting of the conference on Sciences and Techniques of Automatic Control and Computer Engineering, MI-STA 2024

作者： Kshem, Warda Khmag, Asem University of Zawia Faculty of Engineering Department of Computer Engineering Az zawia Libya

ISBN: (纸本)9798350372632

In the field of image denoising, Block Matching 3 Dimensions technique (BM3D) stated as a powerful technique that works to remove white Gaussian noise (A WGN). Despite BM3D shows its great success in comparison with the best denoising methods, still its visual quality decreases as the noise density escalates in noisy digital images. therefore, the need to create a powerful image denoising method is necessary to accomplish the processing of image enhancement applications. the proposed method is introduced by. In this study, discrete wavelet transformation is applied on the LL level of the wavelet decomposition due to its ability to keep the smallest change in the original image. Furthermore, the coefficients of LL will be then divided to small blocks that contain contaminated pixels that suffer from additive white Gaussian noise (A WGN). Comparing with conventional block matching 3D (BM3D) that works well only on the similar patches, our proposed method has the ability to work on similar and dissimilar patches in order to find the inter and intra- correlations between dissimilar pixels. the proposed technique is examined on several digital benchmark images with different noise levels in terms of the quantity of the lost in the original and resulted pixels. In this regard, the performance of the tested images is estimated and then compared proposed with several high quality noise removal techniques according to several assessments such as peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and the figure of merits (FOM). the high amount of these factors reflects the success of the proposed technique. Further, it is interesting to observe the improvement in the running time where it was far less than the investigated noise removal algorithms. © 2024 IEEE.

关键词： image enhancement

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13页 << < 2 3 4 5 6 7 8 9 10 11 > >>

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：