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

14,057 篇 会议
187 篇 期刊文献
29 册 图书

馆藏范围

14,273 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

9,369 篇 工学
- 5,625 篇 计算机科学与技术...
- 3,194 篇 软件工程
- 3,029 篇 信息与通信工程
- 2,648 篇 电气工程
- 1,025 篇 电子科学与技术（可...
- 967 篇 控制科学与工程
- 913 篇 机械工程
- 897 篇 光学工程
- 836 篇 生物医学工程（可授...
- 667 篇 仪器科学与技术
- 595 篇 生物工程
- 492 篇 材料科学与工程（可...
- 312 篇 化学工程与技术
- 171 篇 航空宇航科学与技...
- 157 篇 安全科学与工程
- 150 篇 土木工程
- 148 篇 网络空间安全
- 146 篇 力学（可授工学、理...
- 145 篇 动力工程及工程热...
3,767 篇 理学
- 1,697 篇 数学
- 1,649 篇 物理学
- 736 篇 生物学
- 428 篇 统计学（可授理学、...
- 367 篇 化学
- 329 篇 系统科学
1,376 篇 医学
- 1,264 篇 临床医学
- 392 篇 基础医学(可授医学...
- 253 篇 药学(可授医学、理...
1,039 篇 管理学
- 623 篇 管理科学与工程(可...
- 444 篇 图书情报与档案管...
123 篇 农学
91 篇 法学
65 篇 教育学
59 篇 经济学
56 篇 军事学
22 篇 艺术学
21 篇 文学

主题

1,244 篇 image processing
933 篇 image segmentati...
823 篇 signal processin...
458 篇 feature extracti...
408 篇 signal processin...
380 篇 image coding
360 篇 pixel
323 篇 image edge detec...
288 篇 image enhancemen...
275 篇 image reconstruc...
274 篇 deep learning
257 篇 signal to noise ...
199 篇 cameras
169 篇 neural networks
161 篇 image color anal...
151 篇 discrete wavelet...
144 篇 filtering
142 篇 image restoratio...
142 篇 image analysis
140 篇 data mining

机构

20 篇 institute of inf...
18 篇 chitkara univers...
18 篇 school of inform...
16 篇 university of ch...
16 篇 beijing institut...
12 篇 department of el...
12 篇 maharishi school...
12 篇 signal processin...
12 篇 national laborat...
11 篇 xidian universit...
11 篇 beijing universi...
10 篇 hewlett packard ...
10 篇 centre of interd...
10 篇 ieee
10 篇 university of el...
10 篇 sri lanka instit...
9 篇 university of sc...
9 篇 shenyang institu...
9 篇 the islamic univ...
9 篇 college of mathe...

作者

19 篇 wang wei
16 篇 yang yang
13 篇 li li
13 篇 wei li
13 篇 wang yan
9 篇 wang jing
9 篇 liu ying
9 篇 yang lei
8 篇 lei wang
8 篇 wang lei
8 篇 liu yang
8 篇 wan wanggen
8 篇 zhuo li
8 篇 zhai guangtao
8 篇 malay kishore du...
7 篇 md. rifat hazari
7 篇 wei liu
7 篇 liu jun
7 篇 li min
7 篇 wang chao

语言

13,864 篇 英文
315 篇 其他
104 篇 中文
3 篇 俄文
2 篇 土耳其文
1 篇 德文
1 篇 法文

检索条件"任意字段=3rd International Conference on Image and Signal Processing"

共 14273 条记录，以下是61-70 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：

Enhancing Weakly Supervised Semantic Segmentation through Patch-Based Refinement 13

Enhancing Weakly Supervised Semantic Segmentation through Pa...

引用

13th Iranian/3rd international Machine Vision and image processing conference (MVIP)

作者： Tajrishi, Narges Javid Afshar, Sepehr Amini Kasaei, Shohreh Sharif Univ Technol Dept Comp Engn Tehran Iran

ISBN: (纸本)9798350350494;9798350350500

Weakly-Supervised Semantic Segmentation (WSSS) with image-level labels, commonly uses Class Activation Maps (CAM) to generate pseudo-labels. However, Convolutional Neural Networks (CNNs), with their limited local receptive field, often struggle to identify entire object regions. Recently, the Vision Transformer (ViT) architecture has been employed instead of CNNs to capture long-range feature dependencies, by using the self-attention mechanism. Despite its advantages, ViT tends to overlook local feature details, leading to attention maps with low quality and unclear object details. This paper introduces a novel method to enhance the local details in attention maps by leveraging local patches. These local patches are selected from regions that are more likely to contain the desired objects. By effectively utilizing these local patches during the training and generation stages, the model yields more detailed attention maps. Extensive experiments were conducted on the PASCAL VOC 2012 benchmark dataset to demonstrate the efficacy of the proposed approach. The results show significant improvements (+2.6% mIoU) with minimal computational overhead, underscoring the potential of the proposed method in the field of Weakly-Supervised Semantic Segmentation.

关键词： Weakly-supervised Semantic Segmentation image Classification Deep Learning Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multi-view Mammography image Classification: By using Breast Region Extraction Method and Statistical Features 13

Enhancing Multi-view Mammography Image Classification: By us...

引用

13th Iranian/3rd international Machine Vision and image processing conference (MVIP)

作者： Bidabadi, Neda Shirany Mahmoudzadeh, Elham Isfahan Univ Technol Dept Elect & Comp Engn Esfahan *** Iran

ISBN: (纸本)9798350350494;9798350350500

Breast cancer is one of the most dangerous diseases among women. Different methods are used to diagnose this cancer that among these, imaging and computer-aided systems are more common. In these systems, one of the most important step is preprocessing and removing unnecessary areas of the images, as well as extracting the chest area. In this paper, we present a method that consists of preprocessing, feature extraction, and using a machine learning classifier. In the preprocessing step, we propose a method to extract the region of interest in both angles of mammography images. The proposed novel method includes applying gamma correction thresholding to the images and obtaining two binary images based on the proposed threshold using the Otsu method. Results show the proposed method successfully removes the chest muscle with 98% accuracy. In the next, for feature extraction phase, we utilize three different methods for extracting features. Finally, by employing an Extra tree model classifier, we classify mammography images into normal and abnormal. By incorporating the block-based feature extraction method, we achieve 98% accuracy in classification. Overall, our approach demonstrates the effectiveness of preprocessing and feature extraction for diagnosing breast cancer using mammography images.

关键词： Mammography image Region of Interest Extraction Breast Cancer Statistical Feature Extraction

来源：评论

学校读者我要写书评

暂无评论

Detection of Appearance Defects in Cigarettes Based on AI Artificial Intelligence 24

Detection of Appearance Defects in Cigarettes Based on AI Ar...

引用

3rd international conference on Cyber Security, Artificial Intelligence and Digital Economy (CSAIDE)

作者： Tian, Qiusheng Liu, Qiang Wang, Li Zhang, Kunfeng Henan Zhongyan Ind Ltd Liabil Co Zhumadian Cigarette Factory Zhumadian 463000 Henan Peoples R China

ISBN: (纸本)9798400718212

The detection of appearance defects in cigarettes is a key quality control link in tobacco production. Traditional detection methods rely on artificial vision, which has problems such as strong subjectivity, low efficiency, and susceptibility to errors. This paper proposes a cigarette appearance defect detection method based on Artificial Intelligence (AI), aiming to improve detection efficiency and accuracy. This method utilizes image processing and analysis methods in AI technology, combined with convolutional neural network algorithms, to achieve automated detection and classification of cigarette appearance defects. The experimental results indicate that this method has higher accuracy and detection efficiency.

关键词： cigarette appearance defect detection artificial intelligence deep learning image processing classification

来源：评论

学校读者我要写书评

暂无评论

Research on Software Radio signal processing Technology Based on FPGA for OpenWifi 3

Research on Software Radio Signal Processing Technology Base...

引用

3rd international conference on Electronics and Information Technology, EIT 2024

作者： Lei, Zhiguang Qiu, Xin'An Lei, Zhiyong Lei, Zhijun Lanzhou Institute of Physics Lanzhou China Beijing Racobit Electronic Information Technology Co.Ltd. Beijing China China Electronics Technology Group Corporation 58th Research Institute Wuxi China

ISBN: (纸本)9798350369151

To enhance the real-time performance and efficiency of radio signal processing, this paper takes OpenWifi as an example to explore the application of FPGA technology in communication systems. By implementing key signal processing functions such as signal demodulation, encoding, and filtering, the results show that FPGA's low latency and high configurability significantly improve processing performance. Additionally, optimized resource allocation and algorithm adjustments further enhance system data throughput and stability, demonstrating the potential of FPGA technology in modern wireless communication. © 2024 IEEE.

关键词： Radio communication

来源：评论

学校读者我要写书评

暂无评论

Chaotic image encryption based on finite field bidirectional diffusion and steganography 3

Chaotic image encryption based on finite field bidirectional...

引用

3rd international conference on image processing and Media Computing (ICIPMC)

作者： Liu, Xiang Ding, Dawei Yang, Zongli Anhui Univ Sch Elect Informat Engn Hefei Peoples R China Yuexi Unmanned Aviat Ind Res Inst Anqing Peoples R China Anqing Civil Unmanned Aerial Test Zone Anqing Peoples R China

ISBN: (纸本)9798350386660;9798350386677

This paper proposes an algorithm combining image encryption and steganography which provides double protection for images that need to be kept secret. First, a new Three-Dimensional (3-D) fractional-order memristive Hindmarsh-Rose (HR) neuron model is constructed. It has highly complex and unpredictable dynamic behavior, which can produce complex state transition phenomena such as period, period-doubling bifurcation, chaos and hyperchaos. Then, the finite-field bidirectional diffusion algorithm was used to perform nonrepetitive scrambling and bidirectional diffusion of the image. Finally, the Least Significant Bit (LSB) algorithm is used to hide the encrypted image in the carrier image that is normally transmitted. Experimental results show that the algorithm has a large key space, which is robust, has high computational time efficiency, and can resist various attacks.

关键词： image encryption Steganography Memristive HR neuron model Finite field bidirectional diffusion Least significant bit

来源：评论

学校读者我要写书评

暂无评论

Research on Information processing System Under Computer Artificial Intelligence Big Data Technology 3

Research on Information Processing System Under Computer Art...

引用

3rd international signal processing, Communications and Engineering Management conference, ISPCEM 2023

作者： Peng, Lei Fu, Qiang Li, Zhi Lin, Musong Qian, Yihua Electric Power Research Institute of Guangdong Power Grid Co. Ltd. Guangdong Key Laboratory of Electric Power Equipment Reliability Guangzhou China

ISBN: (纸本)9798350307023

In this paper, a virtual view image post-processing method using background information is proposed. Firstly, a depth-based method is used to deal with overlapping between two images. Secondly, the artifacts of the left and right virtual view are located by the motion direction of the observation point, and the artifacts are eliminated by the background pixels in the supplementary view Angle. Then the background image is filled with holes and combined with the foreground image to form a virtual perspective image. The experimental results show that the peak signal noise of this method is 0.6357 dB better than that of the traditional method. Experiments show that the method proposed in this paper can improve the rendering effect significantly. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Pixel-level Vibration Imaging for Flying Objects with Translational Slide image Sequences 3

Pixel-level Vibration Imaging for Flying Objects with Transl...

引用

3rd international conference on image processing and Robotics, ICIPRoB 2024

作者： Shimasaki, Kohei Okamura, Tomoaki Ishii, Idaku Hiroshima University Graduate School of Advanced Science and Engineering Higashi-hiroshima city Japan

ISBN: (纸本)9798350374766

We propose a pixel-level vibration imaging method for high frame rate (HFR)-video-based localization of flying objects with large movement. When the ratio of the translation speed of a target to its vibration frequency is large, obtaining its frequency response in image intensities becomes difficult because one or no waves are observable at the same pixel. Our method can localize flying and moving objects with fllapping vibration frequency by virtually translating multiple image sequences for pixel-level short-time Fourier transform to observe multiple waves at the same pixel to estimate moving direction. © 2024 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Advancing Industry 4.0 with Real-Time Machine Vision Integration in Cyber-Physical Systems 3

Advancing Industry 4.0 with Real-Time Machine Vision Integra...

引用

3rd international conference on Computing and Machine Intelligence (ICMI)

作者： Hamza, Syed Amir Jesser, Alexander Heilbronn Univ HHN Inst Intelligent Cyber Phys Syst ICPS Heilbronn Germany

ISBN: (纸本)9798350372977;9798350372984

This study introduces a machine vision system integrated into cyber-physical systems (CPS) for enhanced industrial control. The system employs a specialized script for real-time image processing and edge detection, with a focus on precision and speed. Results showcase the system's rapid processing capabilities and high-accuracy feature detection, facilitated by machine learning algorithms that enable adaptability and iterative improvement. The system distinguishes itself by not only providing rapid and accurate feature recognition but also by outputting precise coordinates, crucial for micron-level manufacturing precision. An intuitive human-machine interface ensures seamless operation within industrial workflows. This integration significantly improves automated quality control and operational efficiency, demonstrating the system's potential to advance smart manufacturing in line with Industry 4.0 standards.

关键词： Cyber-Physical Systems (CPS) Machine Vision Systems Real-Time image processing Edge Detection Smart Manufacturing Industry 4.0 Automated Quality Control Machine Learning Algorithms Precision Manufacturing

来源：评论

学校读者我要写书评

暂无评论

Is this Real? image Steganography without Embedding Spoofs Fake image Detector 3

Is this Real? Image Steganography without Embedding Spoofs F...

引用

3rd international conference on image processing and Media Computing (ICIPMC)

作者： Pei, Gang Tang, YunJin Yan, Song Hu, DongHui Hefei Univ Technol Sch Comp & Informat Sci Hefei Peoples R China

ISBN: (纸本)9798350386660;9798350386677

Steganography is a technology that conceals secret information in the carrier in an imperceptible way. Traditional embedding-based steganography are easily detected by steganalysis methods because of the inevitable modifications. Steganography-without-Embedding (SwE) methods benefit from the fact that they do not modify the carrier and can resist the traditional steganalysis which distinguishs stego images from cover images. However, in practice, SwE still face the challenge of fake image *** this paper, we propose a SwE based on adversarial examples to improve steganographic security against both CS-steganalysis (distinguish cover and stego) and RF-steganalysis (distinguish real image and fake image). Two cases of RF-steganalysis, white-box and black-box, are considered. To improve the generator learning ability and the information recovery ability, we introduce the attention module in both the generator and extractor. Experimental results show that the proposed method has considerable extraction rate and could effectively resist both CS-steganalysis and RF-steganalysis.

关键词： Steganography-without-Embedding adversariale examples steganalysis fake image detector

来源：评论

学校读者我要写书评

暂无评论

Cultural-Aware AI Model for Emotion Recognition 13

Cultural-Aware AI Model for Emotion Recognition

引用

13th Iranian/3rd international Machine Vision and image processing conference (MVIP)

作者： Baradaran, Mehrdad Zohari, Payam Mahyar, Abtin Motamednia, Hossein Rahmati, Dara Gorgin, Saeid Shahid Beheshti Univ Dept Comp & Data Sci Tehran Iran Khaje Nasir Univ Technol Dept Comp Engn Tehran Iran Inst Res Fundamental Sci Sch Comp Sci High Performance Comp Lab Tehran Iran Shahid Beheshti Univ Fac Comp Sci & Engn Tehran Iran Chosun Univ Dept Comp Engn Gwangju 61452 South Korea

ISBN: (纸本)9798350350494;9798350350500

Emotion AI is a research domain that aims to understand human emotions from visual or textual data. However, existing methods often ignore the influence of cultural diversity on emotional interpretation. In this paper, we propose a multi-modal deep learning model that integrates cultural awareness into emotion recognition. Our model uses images as the primary data source and comments from individuals across different regions as the secondary data source. Our results show that our model achieves robust performance across various scenarios. Our contribution is to introduce a novel fusion approach that bridges cultural gaps and fosters a more nuanced understanding of emotions. Due to the best of our knowledge, few works are using this approach, for Emotion AI, combining different types of data sources and models. We evaluate our model on the ArtELingo dataset, which contains image-comment pairs with Chinese, Arabic, and English annotations. The experimental results in the evaluation phase demonstrate an impressive 80% recognition accuracy for the model that merges image-text features.

关键词： Emotion Recognition DeepFeature Extraction image Representation Text Representation

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500页 << < 3 4 5 6 7 8 9 10 11 12 > >>

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：