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

4,746 篇 会议
12 篇 期刊文献

馆藏范围

4,758 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,155 篇 工学
- 2,813 篇 计算机科学与技术...
- 2,227 篇 软件工程
- 1,264 篇 信息与通信工程
- 759 篇 控制科学与工程
- 691 篇 生物工程
- 668 篇 光学工程
- 530 篇 电气工程
- 454 篇 生物医学工程（可授...
- 419 篇 电子科学与技术（可...
- 299 篇 网络空间安全
- 182 篇 安全科学与工程
- 163 篇 机械工程
- 160 篇 仪器科学与技术
- 159 篇 交通运输工程
- 152 篇 动力工程及工程热...
- 152 篇 化学工程与技术
- 142 篇 石油与天然气工程
1,643 篇 理学
- 709 篇 生物学
- 637 篇 物理学
- 604 篇 数学
- 242 篇 化学
- 180 篇 统计学（可授理学、...
827 篇 管理学
- 463 篇 图书情报与档案管...
- 443 篇 管理科学与工程(可...
- 119 篇 工商管理
434 篇 医学
- 364 篇 临床医学
- 247 篇 基础医学(可授医学...
- 214 篇 药学(可授医学、理...
- 106 篇 公共卫生与预防医...
125 篇 法学
- 109 篇 社会学
95 篇 农学
45 篇 经济学
44 篇 文学
33 篇 教育学
12 篇 军事学

主题

320 篇 image processing
312 篇 deep learning
231 篇 image segmentati...
191 篇 signal processin...
172 篇 image classifica...
167 篇 image enhancemen...
162 篇 computer vision
140 篇 image recognitio...
138 篇 convolutional ne...
136 篇 feature extracti...
125 篇 training
108 篇 machine learning
83 篇 neural networks
83 篇 computational mo...
79 篇 visualization
78 篇 object detection
71 篇 natural language...
69 篇 semantics
66 篇 accuracy
65 篇 acoustics

机构

24 篇 chitkara univers...
17 篇 maharishi school...
15 篇 lovely professio...
15 篇 tianjin universi...
13 篇 university of ch...
12 篇 the islamic univ...
11 篇 school of comput...
11 篇 centre of interd...
10 篇 peng cheng labor...
10 篇 graphic era hill...
9 篇 national univers...
9 篇 school of comput...
9 篇 vivekananda glob...
9 篇 college of compu...
8 篇 school of comput...
8 篇 maharishi school...
8 篇 gla university d...
8 篇 college of infor...
8 篇 school of comput...
7 篇 college of compu...

作者

13 篇 chauhan rahul
11 篇 yang yang
10 篇 anand vatsala
8 篇 kukreja vinay
8 篇 gupta rupesh
7 篇 luo xiaonan
7 篇 zhao yang
6 篇 pei jihong
6 篇 kumar ankit
6 篇 choudhury tanupr...
6 篇 zhu ce
6 篇 ce zhu
6 篇 kumar gaurav
6 篇 li wei
6 篇 yu li
5 篇 gill kanwarparta...
5 篇 zhiguo cao
5 篇 nagaraj p.
5 篇 singh kamred udh...
5 篇 li qiang

语言

4,706 篇 英文
51 篇 其他
17 篇 中文
1 篇 土耳其文

检索条件"任意字段=2023 IEEE International Conference on Image Processing and Computer Applications, ICIPCA 2023"

共 4758 条记录，以下是4561-4570 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：

A Novel Design and Development model for people counting in a Closed Environment with Machine Learning Approach

A Novel Design and Development model for people counting in ...

引用

Emerging Trends in Industry 4.0 (ETI 4.0)

作者： Praveen Gupta Umashankar Ghugar Chinta Vishnu Vardhan Rakesh Nayak Chaur Singh Rajpoot Department of Computer Science and Engineering GITAM School of Technology GITAM (Deemed to be University) Visakhapatnam India Department of Computer Science and Engineering OP Jindal University Raigarh CG Parul Institute of Technology Parul University Vadodara Gujarat India

image processing can be used to solve some daily applications. computer vision and Artificial Intelligence in the computer system provide the capability to work like the human mind. In the last decade, computer programming is moving towards processing images and finding useful results and analysis. This experiment is an effort to count the number of people in a closed environment. there are many situations when it is required to count the persons in the room. An application can do this work with accuracy and in less time. this can be enhanced to another area where it can count some other objects also. In this experiment efforts have ben done for the identification of people and count them correctly. It has not been tested on large numbers yet. You only look once (YOLO) real time object detection technique is used with some more microenvironments. this can be used for real-life situations and for the safety of any objects. This paper is based on YOLO. The experiments have many benefits and applications in all kinds of industries. in the future, it may be extended to videos.

关键词： Industries computer vision image processing Object detection Machine learning Programming Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Chinese Summarization Generation Method Based on Knowledge Distillation

A Lightweight Chinese Summarization Generation Method Based ...

引用

Information Science, Parallel and Distributed Systems (ISPDS), international conference on

作者： Shiyue Liu Yannan Xiao Xueyong Wang Wenming Huang Zhenrong Deng Guangxi Key Laboratory of Image and Graphic Intelligent Processing School of Computer and Information Security Guilin University of Electronic Technology Guilin China School of Computer and Information Security Guilin University of Electronic Technology Guilin China Guilin Xintong Technology Co. Guilin China

In recent years, large-scale pretrained natural language processing models such as BERT, GPT3 have achieved good results in processing tasks. However, in daily applications, these large-scale language models usually exist large model size or long running time, and the model portability and application are not very convenient. To settle this problem, we come up with a lightweight summarization generation method based on knowledge distillation (LW-BERT-KD, abbreviated as LBK model) to prove that complex neural network knowledge (taking BERT model as an example) can be extracted to lightweight language processing models (taking BiLSTM model as an example), thus achieving the purpose of complex knowledge extraction and model compression. In this paper, the BERT model is regarded as the teacher model, and the BiLSTM is regarded as the student model. The knowledge distillation technology is the transfer of knowledge from teacher models to student models, so that the generated model is effective, lightweight, and easy to port. On the Chinese abstract generation dataset, the training effect of this model is significantly better than the basic Transformer baseline. The experimental results show that if the training parameters are increased by 100 times, the model achieves comparable results with complex preprocessing language models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Techniques for Precise Vehicle Detection and Distance Estimation in Autonomous Systems

Deep Learning-Based Techniques for Precise Vehicle Detection...

引用

ieee international conference on Cloud Computing in Emerging Markets (CCEM)

作者： Srinivasa C Suresha R Manohar N Dharun G K Sheela T Tian Jipeng Department of Computer Science School of Computing Mysuru Amrita Vishwa Vidyapeetham India Department of Computer Science Maharani's Science College for Women (Autonomous) Mysuru India Computer Science College Zhongyuan University of Technology Zhengzhou Henan Province china

ISBN: (数字)9798350360059

ISBN: (纸本)9798350360066

Vehicle detection, recognition, and distance estimation play a crucial role in computer vision, particularly in applications such as intelligent traffic systems. However, existing methods need help in achieving accurate vehicle detection, recognition, and distance estimation, often resulting in low detection accuracy and limited distance estimation capability. This paper proposes an integrated approach combining Faster R-CNN architecture with scale-based distance estimation to address these issues. Through experimental evaluations, the results validate the effectiveness of the proposed method in achieving 93.5%, 95.6%, and high detection accuracy, recognition accuracy, and accurate distance estimation. The proposed framework shows the potential to enhance the performance and robustness of vehicle detection and distance estimation systems, offering promising advancements in this field.

关键词： Accuracy Vehicle detection Estimation Deep architecture Robustness Real-time systems Safety Indexes image enhancement Vehicles

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture Detection using Transfer Learning with Deep Neural Networks

Hand Gesture Detection using Transfer Learning with Deep Neu...

引用

international conference for Convergence of Technology (I2CT)

作者： Thanushree M P Manjula R Bharamagoudra Syeda Zoya Noorain Sharon Maria SP Electronics and Computer Engineering School of Electronics and Communication Engineering REVA University Bangalore India School of Electronics and Communication Engineering REVA University Bangalore India

Large segments of the population value sign language as one of the many languages used for communication. Each sign in each sign language differs in terms of hand shape, motion profile, and positioning of the hand. These differences will have a substantial influence on the accuracy and reliability of the identification process. Therefore, one of the key techniques for detecting gestures is sign language identification utilizing deep learning. In this paper, we have considered four major algorithms of image classification EfficientNet- B0, GoogleNet, ResNext 50 32x4d and MobileNet-V2 which were tested on GPU system. To determine the optimum model that uses the fewest GPU cores, many factors have been considered, including training time, training accuracy, total loss and inference. GoogleNet performance is better as compared to other models.

关键词： Training Deep learning Neural networks Memory management Transfer learning Graphics processing units Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Secret image Authentication Through Encryption-Based Steganography with Reversible Watermarking

Enhancing Secret Image Authentication Through Encryption-Bas...

引用

Mobile Networks and Wireless Communications (ICMNWC), ieee international conference on

作者： P.V. Lakshmi G Sunil Ali Ashoor Issa Kassem Al-Attabi Ghazi Mohamad Ramadan Dept CSE GST GITAM(Deemed to be University) Visakhapatnam India School of Computer Science & Artificial Intelligence SR University Warangal Telangana India National University of Science and Technology Dhi Qar Iraq The Islamic University Najaf Iraq College of MLT Ahl Al Bayt University Karbala Iraq

Reversible data hiding is a special technique primarily used for embedding a secret image that can be later restored from the watermarked image. The image encryption algorithms have been developed based on the Chaotic Logistic-Sine Coupling map (CLSM) While these algorithms perform well in the steganography process there is still room for further development to enhance the level of security they offer. The implementation of the algorithm and its security have been partially analysed using statistical measures like sensitivity to the key space and pixel correlation. Depending on the specific application the CLSM can be computationally intensive making it less suitable for real-time image processing on low-resource devices. To ensure authentication, the MATLAB standard image is exclusively utilized for converting the secret image and embedding it using the Multi-Region Watermark Mechanism (MRWM) designed for color images. In this paper, the Histogram Equalization is utilized feature region is selected and processed and watermarking is performed multiple times due to overlapping feature regions. Comparatively, the results obtained using CLSM show a PSNR of 65.99, MSE of 0.0120, and SSIM of 0.9998 on the MATLAB standard image, surpassing other existing models like Pixel Value Ordering (PVO) and Discrete Cosine Transform (DCT) demonstrating superior image performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Effective Clustering Using Moth Flame Optimization for Content-Based image Retrieval

An Effective Clustering Using Moth Flame Optimization for Co...

引用

Mobile Networks and Wireless Communications (ICMNWC), ieee international conference on

作者： Srinivas Aluvala Zainab Abed Almoussawi Muntather Almusawi Zamen Latef Naser S. Meenakshi Sundaram School of Computer Science & Artificial Intelligence SR University Warangal Telangana India College of Islamic Science Ahl Al Bayt University karbala Iraq The Islamic university Najaf Iraq National University of Science and Technology Dhi Qar Iraq Department of AI and DS Nitte Meenakshi Institute of Technology Bengaluru India

Content-based image retrieval plays an important role in many domains and the volume of the image database increasing tremendously. It is very complex to comparing the query image feature with all images in the dataset during the retrieval phase. Due to computational complexity increase which degrades the performance of recognition accuracy. The proposed model Clustering using Moth Flame Optimizer are pre-processing, feature extraction, feature fusion, clustering and classification. The corel lk dataset is utilized in this research for effective classification of CBIR method. Filter using First Average Peer Group (F APG) is used to remove the noise in the pre-processing stage. Feature extracted using Local Binary Pattern (LBP) and Hue Saturation Value (HSV) based feature extraction techniques. All these two features are fused into single feature using average and weighted technique. Next, proposed model clustering using Moth Flame Optimization algorithm, it enhance the flames and flame value is obtained in ***, the relevant image is retrieved using SAR classifier which utilized Deep Learning (DL) for effective classification. The obtained result shows the proposed clustering using MFO model achieve better accuracy of 99.87% on Corel lk dataset which insure accurate classification compared to other existing methods like Bi-Iayer method and Texture from semantic pyramid.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge-Preserving Multi-Exposure Fusion with Guided Filtering for Structural Patch Decomposition

Edge-Preserving Multi-Exposure Fusion with Guided Filtering ...

引用

ieee international conference on Electronic Information and Communication Technology (ICEICT)

作者： Yang Zhen Junwei Qi Yingsong Li College of Information and Communication Engineering Harbin Engineering University Harbin China College of Computer Science and Technology Harbin Engineering University Harbin China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

Multi-exposure image fusion (MEF) is one of the effective ways to obtain high dynamic range (HDR) images. Multi-scale structural patch decomposition based MEF(MSPD) and edge-preserving structural patch decomposition (MESPD) have achieved state-of-the-art fusion quality. MESPD incorporates edge-preserving factors into MSPD to preserve details in a single-scale setting. However, we find that the edge-preserving factors put too much emphasis on the edge, resulting in artifacts on some edges and loss of details. To tackle this issue, guided filter is introduced into MSPD, which is directly used as an edge-preserving filter instead of mean filter to implicitly decompose images. In addition, we have designed a flexible adaptive weight, which can further maintain details of the light and dark areas. Likewise, we inherit MESPD and MSPD to extend our method to multi-scale framework. Extensive experimental results demonstrate our method can produce satisfactory results in both static and dynamic scenes with fewer artifacts and low computational cost.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EDRNet: A Lightweight Underwater Sonar Target Detection Model Based on an Efficient De-Redundancy Network

EDRNet: A Lightweight Underwater Sonar Target Detection Mode...

引用

ieee Joint international Information Technology and Artificial Intelligence conference (ITAIC)

作者： Qiuqin Fang Jianxun Tang Zhe Chen Mingsong Chen School of Information and Communication Guilin University of Electronic Technology Guilin China School of Ocean Engineering Guilin University of Electronic Technology Guilin China Cognitive Radio and Information Processing Key Laboratory Authorized by China's Ministry of Education Foundation Guilin University of Electronic Technology

Underwater object detection is one of the hot research topics in the field of acoustic signal processing. Using sonar to automatically detect seabed objects has significant importance for marine resource development and underwater military training. Traditional sonar image detection methods based on machine learning and clustering have problems such as large model parameters, redundant computation, low detection accuracy, and difficult deployment in practical engineering applications. To address these issues, this paper proposes a lightweight underwater sonar object detection model named EDRNet. First, it introduces the lightweight network EfficientFormerV2, which solves the problems of large model parameters and redundant computation. Second, it introduces the SimSPPF module, which enlarges the receptive field of the network. Finally, it adds the parameter-free attention mechanism SimAM, which enhances feature extraction and improves model computation efficiency and detection accuracy. Experiments on the SeabedObjects-KLSG dataset and the STCD dataset show that the proposed model achieves an average detection accuracy of 94.7%, which is 22.8%, 1.8%, 2.3%, and 0.4% higher than the existing mainstream models Faster R-CNN, YOLOv3, YOLOv4, and YOLOv5, respectively. The parameter size is 58.6% of YOLOv5s, and the computation amount is 51.25% of YOLOv5s. This verifies that the proposed model effectively reduces the model size while maintaining performance and has stronger practical significance for underwater sonar image detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of Bacterial Leaf Blight Disease Using RGB-Based Vegetation Indices and Fuzzy Logic

Detection of Bacterial Leaf Blight Disease Using RGB-Based V...

引用

international Colloquium on Signal processing & Its applications, CSPA

作者： Nor Hafiza Aziz Rohayu Haron Narashid Tajul Rosli Razak Siti Aminah Anshah Noorfatekah Talib Zulkiflee Abd Latif Norhashila Hashim Khairulazhar Zainuddin Centre of Studies Surveying Science & Geomatics Faculty of Architecture Planning & Surveying Universiti Teknologi MARA Arau Perlis MALAYSIA Faculty of Computer and Mathematical Sciences Shah Alam selangor MALAYSIA College of Build Environment (of Affiliation) Shah AlamSelangor MALAYSIA Faculty of Engineering Universiti Putra Malaysia Johor Bahru Johor MALAYSIA

Paddy planting becomes the primary source of income and livelihood for paddy farmers, especially small-scale farmers and landless laborers. Unfortunately, rice production has been threatened by paddy disease. The bacteria leaf blight disease (BLB) is one of Malaysia’s most significant paddy diseases, causing substantial harm to rice production. This study aims to determine the bacteria leaf blight (BLB) disease from the utilized techniques of RGB-Based Vegetation Indices and Fuzzy Logic on the Unmanned Aerial Vehicle (UAV) images during the first paddy season 2022 in Perlis. In this study, the RGB-based indices of Normalized Green Red Different Index (NGRDI) and Green Leaf Index (GLI) were applied to the UAV images captured at 20m altitudes. Then the fuzzy logic classification technique was applied to identify the BLB disease severity which consists of healthy and infected paddy leaves with the acceptable accuracy of 90.16%. Based on the classified BLB severeness with fuzzy logic, the result shows that the NGRDI was more significant to identify paddy disease in the area. In contrast, the GLI index is more significant to identify the non-paddy area. The NGRDI and GLI index ranges for BLB were found between -0.054 to 0.092 and 0.005 to 0.222. For more improvement of the study, the multispectral UAV image should be applied to increase the accuracy of paddy disease detection like BLB and the images will also be taken and verified in other paddy plots with the aid of a spectroradiometer.

关键词： Fuzzy logic Spectroradiometers Microorganisms image recognition Vegetation mapping Production Autonomous aerial vehicles

来源：评论

学校读者我要写书评

暂无评论

Bowler's Real-Time Posture Assessment Using Integrated Moving Body and Frame Difference with Kinect and image processing Algorithms

Bowler's Real-Time Posture Assessment Using Integrated Movin...

引用

international conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM)

作者： Jessie R. Balbin Flordeliza L. Valiente Christian Rae S. Dela Cruz John Robin G. Gregorio Patrick Carlo J. Tinaya Joel Andrew P. Villarba School of Electrical Electronics and Computer Engineering Mapua University Intramuros Philippines

ISBN: (数字)9798350381177

ISBN: (纸本)9798350381184

This paper discusses a system that detects bowling posture and corrects it by image analysis using frame difference and image processing algorithms. Using a Kinect as the main sensor, we were able to create a system that uses skeletal imaging to obtain coordinate data of the body which is converted to angle form and compared with a reference with a set tolerance. Python was used as the main programming language because of the easy integration of the Py Kinect library that is responsible for the manifestation of the skeletal frame on the subject. The four-step approach was used as the reference for the correct bowling posture and was assessed by a professional bowler. The results taken were also shown to the coach to ensure accuracy. Correlation Analysis was used as the statistical tool to prove the similarity of the data taken from the program and the evaluation of the professional coach.

关键词： Training Legged locomotion Statistical analysis Imaging Process control Real-time systems Libraries

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476页 << < 453 454 455 456 457 458 459 460 461 462 > >>

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：