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

4,604 篇 会议
498 册 图书
70 篇 期刊文献

馆藏范围

5,171 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

3,380 篇 工学
- 2,744 篇 计算机科学与技术...
- 1,816 篇 软件工程
- 723 篇 信息与通信工程
- 720 篇 光学工程
- 667 篇 电气工程
- 415 篇 生物工程
- 359 篇 控制科学与工程
- 348 篇 生物医学工程（可授...
- 234 篇 机械工程
- 222 篇 电子科学与技术（可...
- 125 篇 仪器科学与技术
- 122 篇 化学工程与技术
- 116 篇 安全科学与工程
- 95 篇 交通运输工程
- 90 篇 材料科学与工程（可...
- 67 篇 建筑学
- 57 篇 土木工程
1,679 篇 理学
- 925 篇 物理学
- 721 篇 数学
- 452 篇 生物学
- 203 篇 统计学（可授理学、...
- 119 篇 化学
- 57 篇 系统科学
488 篇 管理学
- 268 篇 图书情报与档案管...
- 240 篇 管理科学与工程(可...
- 78 篇 工商管理
439 篇 医学
- 418 篇 临床医学
- 127 篇 基础医学(可授医学...
- 89 篇 药学(可授医学、理...
60 篇 法学
- 59 篇 社会学
54 篇 农学
35 篇 教育学
31 篇 艺术学
29 篇 经济学
11 篇 文学
10 篇 军事学

主题

817 篇 computer vision
624 篇 pattern recognit...
534 篇 image processing
353 篇 image processing...
347 篇 artificial intel...
337 篇 image segmentati...
279 篇 feature extracti...
208 篇 image recognitio...
174 篇 deep learning
155 篇 computer graphic...
151 篇 computer imaging...
140 篇 face recognition
123 篇 machine learning
123 篇 object recogniti...
117 篇 convolutional ne...
114 篇 image analysis
113 篇 object detection
108 篇 information syst...
105 篇 cameras
104 篇 computational mo...

机构

25 篇 istituto italian...
24 篇 google deepmind ...
24 篇 meta ai barcelon...
23 篇 politecnico di t...
14 篇 national center ...
14 篇 institute of ima...
10 篇 shanghai jiao to...
10 篇 tsinghua univers...
10 篇 university of ch...
10 篇 institute of aut...
9 篇 institute of ima...
9 篇 computer vision ...
8 篇 indian statistic...
8 篇 inria nancy gran...
8 篇 dalian universit...
8 篇 icube université...
8 篇 erasmus mc - uni...
8 篇 tencent jarvis l...
8 篇 university of ba...
7 篇 department of co...

作者

24 篇 cristian canton
24 篇 alessio del bue
24 篇 tatiana tommasi
24 篇 jordi pont-tuset
17 篇 de-shuang huang
14 篇 stefanie speidel
12 篇 wilfried philips
10 篇 mohamed kamel
9 篇 paul scheunders
9 篇 h. bischof
9 篇 jie yang
9 篇 stéphane cotin
9 篇 dan popescu
8 篇 umapada pal
8 篇 aurélio campilho
8 篇 yefeng zheng
8 篇 kok wai wong
8 篇 christian barill...
8 篇 ilias maglogiann...
8 篇 tieniu tan

语言

4,855 篇 英文
296 篇 其他
65 篇 中文

检索条件"任意字段=4th International Conference on Computer Vision, Pattern Recognition and Image Processing"

共 5172 条记录，以下是581-590 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：

Refining U-Net Architecture through Genetic Algorithms for Improved Skin Lesion image Segmentation 4th

Refining U-Net Architecture Through Genetic Algorithms for I...

引用

4th international conference on Intelligent Systems and pattern recognition-ISPR

作者： El Abassi, Fouzia Darouichi, Aziz Ouaarab, Aziz Cadi Ayyad Univ Comp & Syst Engn Lab L2IS FSTG Marrakech 40000 Morocco

ISBN: (纸本)9783031821554;9783031821561

Recently, various approaches using manually designed convolutional neural networks (CNNs) and U-shaped (encoder-decoder) models have yielded encouraging results in the automatic segmentation of medical images. Nevertheless, the manual construction of these models is laborious, requires a high level of expertise, is time-consuming, error-prone and can result in the loss of crucial details. To improve segmentation performance, these models often incorporate numerous parameters, which can lead to problems such as overfitting, vanishing and exploding gradient and increased computational complexity. In this study, we implement a genetic algorithm (GA) specifically designed for a U-Net architecture to segment images of skin lesions, using two datasets ISIC-SMALL1 and ISIC-SMALL2 constructed from ISIC-2017 dataset. the main objective is to optimize internal block topologies within the U-Net, in order to identify a high-performance deep neural network with a minimum of parameters. Compared to the U-Net baseline, our proposed methodology demonstrates favorable outcomes in terms of both the number of trainable parameters and Intersection over Union (IoU). For the ISIC-SMALL1 dataset, the leading model surpasses U-Net with a reduced parameter count (0.352001M) and an elevated IoU score (0.826052 vs. 0.736352). Similarly, the second-best model outperforms U-Net with fewer parameters (0.258781M vs. 31.043586M) and a higher IoU score (0.821956 vs. 0.736352). In the ISIC-SMALL2 dataset, both top models outshine U-Net in IoU (0.753122 and 0.722079 vs. 0.725363, respectively) while maintaining lower parameter counts.

关键词： Medical image Segmentation Convolutional Neural Networks (CNNs) U-Net architecture Genetic Algorithms (GA) Skin Lesion

来源：评论

学校读者我要写书评

暂无评论

Improved Deep Learning-based Contactless Biometric recognition using Bracelet Lines 4

Improved Deep Learning-based Contactless Biometric Recogniti...

引用

4th international conference on Distributed Sensing and Intelligent Systems, ICDSIS 2023

作者： Duggal, Ritwik Pandya, Aarya Rathore, Rajkumar Singh Kalra, Khwab Sharma, Kanak Gupta, Nitin Department of Computer Science and Engineering National Institute of Technology Himachal Pradesh Hamirpur India Cardiff School of Technologies Cardiff Metropolitan University United Kingdom Department of Electrical Engineering National Institute of Technology Himachal Pradesh Hamirpur India

ISBN: (纸本)9781839539954

this study explores the integration of deep learning and computer vision techniques for contactless biometric identification, specifically focusing on wrist bracelet lines. In an era where biometric identification plays a pivotal role in various sectors, including personal identity, mobile devices, and smart gadgets, this research addresses the heightened demand for efficient contactless solutions, amplified by the COVID-19 pandemic. While conventional methods such as finger knuckle, face recognition, and fingerprint analysis have been prevalent, this research introduces an innovative approach that capitalizes on the distinct and enduring patterns observed in wrist bracelet lines. the proposed system employs advanced deep learning methodologies, notably the YOLO (You Only Look Once) model for precise wrist detection. To facilitate image capture and transmission for identification, a combination of an Arduino Uno and an ESP32 CAM module is employed. the study highlights the system’s real-time recognition capabilities through comprehensive results, emphasizing its potential for secure, efficient, and contactless biometric identification in Smart city applications. © the Institution of Engineering & Technology 2023.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Athletic Performance:2D Human Pose Estimation Using Deep Neural Networks for Movement Analysis 7

Enhancing Athletic Performance:2D Human Pose Estimation Usin...

引用

7th international conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Devi, Pothreddypally Jhansi Sumani, Aleshwaram Chandra, Chenna Mukesh thrisha, Battu Bhanu Vamshi, Arkatala Sai B V Raju Institute of Technology Dept. of Computer Science Engineering Telangana India

ISBN: (纸本)9798350372816

computer vision is a field that is used to build many neural network-based prototypes efficiently. It analyses images and videos effectively and processes them digitally. Human Pose estimation (HPE) is one of the computer vision applications which additionally uses neural networks for prediction. Human pose estimation is used widely in many fields which includes action recognition, fitness, gaming, and motion capture. HPE identifies and locates the key points on the body joints of a person's body. these body points are connected to form a Skeletal Structure. this skeletal representation helps to easily visualize the image in 2-D. Focusing on Sports domain, HPE plays major role in estimating athlete movements. It helps in analyzing the feedback on the posture which allows to make adjustments during training. It also helps viewers to analyse the insights of athlete performance. To achieve the model that contains all these features, requires involvement of few frameworks. OpenPose is utilised for fast processing of videos and can detect the multiple people in one frame. OpenPose has the capability of handling the occulsion. On the Other hand, the model also import the capabilities of HRNet, which is used for analyzing athlete movements and tracks the gestures. After detecting the keypoints on the body joints, these points must be integrated to form 2-D images. To achieve the spatial relationship between the bodypoints Joint Graph Convolutional Neural Networks (JGCN) framework is used. the proposed model is estimated to generate approximately (4- 5)percent more efficiency and accuracy in its output 2-D image compared with the previous models. © 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

Investigation of Machine Learning Algorithms for pattern recognition in image processing 5

Investigation of Machine Learning Algorithms for Pattern Rec...

引用

5th international conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Kate, Chennaiah Kalpana, C. Sharma, Arvind Yadav, Ajay Singh Kumar, Ashok Kumar, S. Sandeep St. Peter's Engineering College Department of Information Technology Telangana Hyderabad500100 India Npr College of Engineering & Technology Department of Computer Science and Engineering Tamil Nadu Dindigul624401 India Government Women Engineering College Department of Electronics and Communication Engineering Rajasthan Ajmer305002 India Srm Institute of Science and Technology Department of Mathematics Uttar Pradesh Ghaziabad201204 India BanasthaliVidyapith Department of Computer Science Rajasthan 304022 India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh 522502 India

ISBN: (纸本)9798350321425

In order to recognize patterns in images, this study tests the performance of many 'machine learning algorithms' and feature extraction methods. Here, synthetic photographs of handwritten digits are used to compare the performance of four machine learning methods ('deep learning, support vector machines, decision trees, and random forests') and two feature extraction strategies (raw pixel values and Histogram of Oriented Gradients). the efficacy of each algorithm is measured in terms of its 'accuracy, precision, recall, and F1 score', among others. Our findings also demonstrate that the Histogram of Oriented Gradients feature extraction method is good at collecting local gradient information in pictures and that deep learning and support vector machines obtain the best accuracy overall. the results of our research have significant ramifications for the future of machine learning techniques used in computer vision and handwriting recognition. Research in the future may test these methods on other datasets and picture kinds, or look into alternative feature extraction strategies and machine learning algorithms. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Research on image Tibetan Caption Generation Method Fusion Attention Mechanism

Research on Image Tibetan Caption Generation Method Fusion A...

引用

pattern recognition and Machine Learning (PRML), IEEE international conference on

作者： Jianjun Xia Xin Yang Qiong Ni Dingguo Gao School of Information Science and Technology Tibetan Information Technology Innovative Talent Cultivation Demonstration Base Tibet University Lhasa China

image caption generation combines computer vision and natural language processing to generate natural language descriptions of images. With the rapid development of deep learning, the performance of end-to-end image caption generation research based on Chinese and English datasets has been improved. However, there is a lack of Tibetan caption data samples for low-resource languages, and the research on image Tibetan caption generation is almost blank. therefore, in order to promote the research and development of multilingual image generation and improve the accuracy of Tibetan image caption, VGG19, InceptionV3 and ResNet101 are used as the backbone network, and group convolution is used to replace the fully connected operation of the attention mechanism. A CNN-based An image Tibetan caption generation method that integrates with the LSTM encoding and decoding network to improve the attention mechanism. Experiments on the Flickr8K and Flickr30K-tic Tibetan caption datasets show that this method is superior to the traditional attention mechanism image caption generation method, and has achieved better performance improvement in BLEU and ROUGE-L image caption evaluation indicators.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Basketball Scoring and Player Performance Tracking System Utilizing AI-Powered Court vision Technology 7

Real-Time Basketball Scoring and Player Performance Tracking...

引用

7th international conference on image Information processing, ICIIP 2023

作者： Muthaiah, U. Sonai, Veeramani Ranjith Kumar, M. Kumar, Sachin Computer Science And Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Shiva Nadar University Computer Science And Engineering School of Engineering Chennai kalavakkam India Maths Amrita School of Engineering Amrita Vishwa Vidyapeetham Chennai India

ISBN: (纸本)9798350371406

Basketball is a very popular sport, and artificial intelligence (AI) has attracted a lot of attention because it can help with player training, help coaches come up with winning strategies, lessen injuries related to sports, and make the game more enjoyable overall. To precisely track and record player scores in real-time, this article presents an inventive AI-based automated basketball scoring system that makes use of computer vision and deep learning techniques. Using a variety of libraries, including TensorFlow, Fast RCNN, OpenCV, Yolov4, Yolov7, and the mmpose tool, the system uses pose recognition, basketball and hoop detection, and tracking techniques. this technology increases the effectiveness of player training by updating scoreboards and game data on its own. the suggested approach has an average accuracy of 78.74% for identifying objects, 83.75% for detecting shots, and 80% for identifying the shooter. the accuracy of the scoring system in allocating scores to shots is 66.67%. this technology is a significant development in the field of sports analytics, improving the experience of analyzing basketball games and maybe opening up new applications for real-time monitoring situations and other sports. Future research will concentrate on broadcast content analysis and real-time deployment. © 2023 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Sign Language recognition Using Convolutional Neural Network 4th

Sign Language Recognition Using Convolutional Neural Network

引用

4th international conference on Advanced Network Technologies and Intelligent Computing-ANTIC-Annual

作者： Potluri, Tejaswi Vallurupalli Nageswara Rao Vignana Jyothi Inst En Vignana Jyothi NagarPragathi Nagar Hyderabad 500090 Telangana India

ISBN: (纸本)9783031837920;9783031837937

Sign language detection is essential for improving accessibility, communication, and inclusion for individuals who are deaf or hard of hearing. this technology enables smooth communication across various environments, including schools, workplaces, healthcare settings, and everyday interactions. By accurately interpreting sign language gestures, it bridges communication barriers, providing equal access to information and services. In education, sign language detection supports language learning and academic success for deaf students, while in healthcare, it ensures that medical information is conveyed accurately, enhancing care quality. In the workplace, it fosters inclusivity by enabling communication between deaf employees and their colleagues, promoting equal opportunities and professional growth. Additionally, during emergencies, it can save lives by enabling swift communication with emergency responders. this study presents a robust sign language detection system based on convolutional neural networks (CNNs), trained on a dataset of 2,515 images representing 36 distinct ASL gestures. the system employs a comprehensive preprocessing pipeline, with images standardized, resized, and split for training and validation, resulting in an accuracy rate of 85.87% across ASL letters and numerals. Real-time testing, facilitated by OpenCV's video capture, demonstrates the model's effectiveness in live gesture recognition with minimal delay. Despite minor errors in misclassification and occlusion, the system shows strong potential to support inclusive communication across settings and to further advance sign language recognition technology.

关键词： Convolutional neural networks image processing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Leather Surface Defect Detection Based on Improved Yolov8 4

Leather Surface Defect Detection Based on Improved Yolov8

引用

4th international conference on computer Science and Management Technology, ICCSMT 2023

作者： Jin, Xuesong Li, Congcong Harbin University of Commerce Heilongjiang Harbin150028 China School of Computer and Information Engineering Harbin University of Commerce Harbin Heilongjiang150028 China

ISBN: (纸本)9798400709517

Addressing the current limitations in computer vision regarding leather defect detection, including issues like low recognition accuracy, imprecise detection, and slow processing speed using traditional network models, this study introduces an optimization approach based on YOLOv8n. In this research: the Faster Block structure is integrated with the original C2f, replacing the Bottleneck module. the new C2f-Faster module replaces a portion of the C2f module in the original model. this not only reduces model parameters but also enhances detection speed and accuracy. the loss computation incorporates the SIoU boundary loss function instead of the actual loss function. this enhancement improves bounding box regression performance and enhances overall accuracy. Experimental results demonstrate that the optimized model achieves a 1.5% increase in mean average precision (mAP) and an 18.7% boost in frames per second (FPS) compared to the original model on the leather defect dataset used in this study. In conclusion, this paper's model significantly enhances detection speed and accuracy, surpassing comparative algorithms and offering valuable practical applications. © 2023 ACM.

关键词： Leather

来源：评论

学校读者我要写书评

暂无评论

Machine vision-Based Structural Diagnosis Application 4th

Machine Vision-Based Structural Diagnosis Application

引用

4th international conference on Advances in Civil and Ecological Engineering Research, ACEER 2022

作者： Hong, Weixing Noori, Mohammad Jiang, Hanqing Liu, Yuhan Altabey, Wael A. Nanjing Zhixing Information Technology Co. Ltd. Jiangsu Nanjing China Jiangsu Advance Transportation Institute Jiangsu Nanjing China Department of Mechanical Engineering California Polytechnic State University San Luis ObispoCA93405 United States Department of Mechanical Engineering Faculty of Engineering Alexandria University Alexandria21544 Egypt

ISBN: (纸本)9789811957826

the wide development in deep learning (DL) application in different fields such as speech recognition, computer vision, and natural language processing has been done by different architectures of networks, such as the most applied network named convolutional neural networks (CNN). this work discusses the framework for monitoring the structural surface cracks based on DL. the proposed model is combined with unmanned aerial vehicles (UAVs) to collect the surface cracks images automatically to detect the cracks in real-time. Equipped with a comparatively heterogeneous dataset, the use of DL allows the crack detection development system. In this proposed work, the results dataset has a high accuracy rate (P%), regression rate (R%), and F-score (F%), and the overall performance is $$95.5{\text{\% }},{ }93.78{\text{\% }}$$, and $$91.55{\text{\% }}$$, respectively. © 2023, the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Design of Gesture recognition System Based on OpenCV 4

Design of Gesture Recognition System Based on OpenCV

引用

4th international Symposium on Smart and Healthy Cities, ISHC 2022

作者： Duan, Chenxu Luo, Shiqiang School of Mechanical Engineering Sichuan University Jinjiang College Meishan620680 China

ISBN: (纸本)9781665491808

As a new type of human-computer interaction, gesture recognition has gradually become an important research direction in the field of smart city construction. the traditional gesture recognition system relies on various types of sensors, which has high requirements for hardware and application environment. the recognition accuracy will be affected by the accuracy and service life of electronic components. therefore, there is an urgent need for natural and easy-to-understand, people-oriented new recognition technology based on computer platform. the OpenCV used in this paper is an open source computer vision library, which contains a wealth of image processing algorithms, which can be easily and quickly applied to gesture recognition systems. this paper makes a complete exploration of gesture recognition system based on OpenCV. Firstly, this paper studies the advantages and disadvantages of different skin color models for skin color detection, and selects a skin color model that is robust in both normal indoor environment and strong light conditions. Secondly, the gray image segmented by skin color is morphologically processed, and the contour frame of gesture information is taken by Fourier descriptor algorithm to obtain the position and boundary information of hand skin color region. then, this paper extracts and calculates the characteristics of the collected data, and uses the support vector machine algorithm to analyze the gesture recognition of the image captured by the camera. Finally, the above research modules are effectively collected, and the graphical interface is written by PyQT5 for human-computer interaction. the system design framework and the specific process of implementing the system are given. then a relatively complete experiment was carried out on the system to verify the accuracy of the recognition. © 2022 IEEE.

关键词： image segmentation

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 << < 55 56 57 58 59 60 61 62 63 64 > >>

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：