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

10,889 篇 会议
406 册 图书
211 篇 期刊文献

馆藏范围

11,506 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

6,674 篇 工学
- 4,903 篇 计算机科学与技术...
- 2,595 篇 软件工程
- 1,631 篇 电气工程
- 1,436 篇 光学工程
- 1,112 篇 控制科学与工程
- 1,011 篇 信息与通信工程
- 858 篇 机械工程
- 428 篇 生物工程
- 389 篇 电子科学与技术（可...
- 351 篇 材料科学与工程（可...
- 330 篇 生物医学工程（可授...
- 321 篇 仪器科学与技术
- 210 篇 化学工程与技术
- 160 篇 交通运输工程
- 151 篇 安全科学与工程
- 102 篇 土木工程
- 85 篇 农业工程
3,016 篇 理学
- 2,354 篇 物理学
- 722 篇 数学
- 470 篇 生物学
- 202 篇 统计学（可授理学、...
- 196 篇 化学
- 93 篇 系统科学
1,208 篇 医学
- 1,145 篇 临床医学
- 146 篇 基础医学(可授医学...
- 102 篇 药学(可授医学、理...
841 篇 管理学
- 593 篇 管理科学与工程(可...
- 276 篇 图书情报与档案管...
- 123 篇 工商管理
177 篇 农学
- 163 篇 作物学
52 篇 法学
51 篇 经济学
49 篇 教育学
28 篇 文学
16 篇 艺术学
10 篇 军事学

主题

2,567 篇 machine vision
2,110 篇 image processing
1,898 篇 computer vision
927 篇 image segmentati...
808 篇 feature extracti...
790 篇 machine learning
581 篇 cameras
462 篇 deep learning
396 篇 image edge detec...
332 篇 pattern recognit...
330 篇 object detection
322 篇 computational mo...
278 篇 support vector m...
268 篇 accuracy
253 篇 neural networks
238 篇 training
236 篇 visualization
228 篇 image recognitio...
203 篇 image color anal...
201 篇 pixel

机构

31 篇 university of no...
31 篇 university of ox...
29 篇 graz university ...
28 篇 university of fr...
26 篇 istituto italian...
24 篇 google deepmind ...
24 篇 meta ai barcelon...
23 篇 politecnico di t...
20 篇 university of sc...
19 篇 center for machi...
17 篇 center for machi...
15 篇 tsinghua univers...
14 篇 university of ch...
13 篇 itmo univ st pet...
13 篇 department of el...
12 篇 harbin institute...
10 篇 shanghai jiao to...
10 篇 school of mechat...
10 篇 tongji universit...
10 篇 institute of aut...

作者

31 篇 andrea vedaldi
31 篇 horst bischof
30 篇 jan-michael frah...
30 篇 thomas brox
24 篇 cristian canton
24 篇 alessio del bue
24 篇 tatiana tommasi
19 篇 de-shuang huang
17 篇 ghassemian hassa...
15 篇 hassan ghassemia...
13 篇 abdenour hadid
12 篇 soltanian-zadeh ...
11 篇 miller jwv
11 篇 bryan scotney
11 篇 wang wei
10 篇 lensu lasse
10 篇 paul f. whelan
10 篇 hong liu
10 篇 voronin viachesl...
10 篇 maryam imani

语言

11,179 篇 英文
251 篇 其他
85 篇 中文
9 篇 土耳其文
2 篇 俄文
1 篇 西班牙文
1 篇 法文

检索条件"任意字段=Iranian Conference on Machine Vision and Image Processing"

共 11506 条记录，以下是241-250 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：

Automated Cricket Commentary Generation for Videos 8th

Automated Cricket Commentary Generation for Videos

引用

8th International conference on Computer vision and image processing (CVIP)

作者： Yadav, K. Shashank Lohith, V. Sachin, M. S. Patil, Madan V. Narayan, Surabhi PES Univ Dept Comp Sci & Engn Bengaluru India

ISBN: (纸本)9783031581809;9783031581816

Cricket is one of the most popular sports in theworld, and its fan base is growing rapidly. However, the quality of the commentary during cricket matches can varywidely, and it often relies on the subjective opinions of the commentators. In this paper, we present a groundbreaking approach to auto-generate cricket commentary using state-of-the-art computer vision and machine learning techniques. Our framework can automatically identify different events happening in a cricket video and produce insightful and engaging commentary based on the state of the game. We focus on the six essential cricket shots played by the batsman, including the Straight Drive, Cover Drive, Lofted shot, Sweep shot, and Cut Shot, and use a machine learning model to recognize each of these shots based on visual signals within the video. Along with that the length and line for the type of ball bowled has been analysed which facilitates a overall complete commentary. We also incorporate relevant data, such as the score, stage of the game, and players involved, to create contextually appropriate commentary. Our approach has the potential to revolutionize the field of sports commentary, providing a new and immersive experience for cricket fans worldwide. With our innovative approach, we believe that auto-generated commentary can become an integral part of the live sports viewing experience, enhancing fan engagement and providing new opportunities for sports broadcasters and content creators.

关键词： computer vision machine learning auto-generation

来源：评论

学校读者我要写书评

暂无评论

Design of a miniaturized optical system for machine vision angular displacement sensors

Design of a miniaturized optical system for machine vision a...

引用

2024 International conference on Optoelectronic Information and Optical Engineering, OIOE 2024

作者： Liang, Shitong Gai, Fangqin Wang, Li Beijing Institute of Control Engineering No.16 South Third Street Zhong-guan-cun Haidian District Beijing China

ISBN: (数字)9781510680470

ISBN: (纸本)9781510680463

machine vision angular displacement sensors have the characteristics of high precision and high reliability, gradually becoming a new technological development direction for angular displacement sensors. The optical system is one of the key components for machine vision angular displacement sensors to achieve high-precision measurement. This article presents an optical system design for a machine vision based angular displacement sensor. The optical system consists of two lenses, with a total optical length of only 8.9mm. The 80% geometric encircled radius is less than 14.1um, and the maximum distortion value is 1.6um. It has the characteristics of miniaturization and high image quality. The processing and assembly of the optical system have been completed, and the optical system has been tested on an angular displacement sensor prototype. Through analysis of the measured image data, the value of the encoded stripe edge in the image is approximately 16.5um, which is basically consistent with the design value. The imaging performance of the designed optical system was tested through experiments, and the correctness of the design theory and results was verified. © 2024 SPIE.

关键词： Optical systems

来源：评论

学校读者我要写书评

暂无评论

Chip Surface Character Detection System Based on machine vision 4

Chip Surface Character Detection System Based on Machine Vis...

引用

4th International conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology, CEI 2024

作者： Liao, Cheng Zhan, Chunlian He, Weiheng Gao, Han Zhou, Peisong School of Optics and Electronic Technology China Jiliang University Hang Zhou China Haining Academy of Integrated Circuit and Advanced Manufacturing Jia Xing China

ISBN: (纸本)9798350378542

A machine vision based chip surface character detection system has been designed to address the defects caused by characters on the chip surface in actual production. The system includes an image acquisition device and software processing algorithms. Firstly, extract the region of interest (ROI) of the chip character by inputting a template image. Then, the template character image is segmented into individual characters using the connected domain labeling method, and a template character library is established. Secondly, based on the template matching method, obtain the best matching position coordinates and extract the geometric features of the characters. Finally, characters are detected based on the number of connected domains, area and perimeter features, Hu moment, centroid coordinates, and edge contours. The experimental results show that the method used can effectively segment characters affected by defects and accurately detect the presence of defects on the chip surface characters. © 2024 IEEE.

关键词： machine vision

来源：评论

学校读者我要写书评

暂无评论

Design Of Convolution Neural Network For Crack Detection 7

Design Of Convolution Neural Network For Crack Detection

引用

7th International conference on Devices, Circuits and Systems (ICDCS)

作者： Malathi, D. Gautham, S. Dineshkumar, M. Balakrishnan, K. Kongu Engn Coll Dept Elect & Commun Engn Erode India

ISBN: (纸本)9798350350470;9798350350487

Crack is an important factor to consider when assessing the quality of concrete structures since it impacts the structure's longevity, application, and safety. Convolutional neural networks are increasingly the best option to replace manual crack detection because of the advancement of methods for deep learning. machine learning algorithms known as artificial neural networks (ANNs) imitate how the human brain functions. These Neural Networks can be implemented in software. However, these neural networks require large computations. Hardware implementation of these neural networks has higher processing speeds than their software implementations. CNN is a particular kind of artificial neural network that is used to interpret pixel data and is utilised in image detection and processing. Computer vision applications including object identification, image segmentation, and image classification work well with convolutional neural networks. employed for categorization The proposed method uses a configurable convolution neural network system for crack detection. An accuracy of 97.5% is achieved over 200 images. By detecting the crack effectively using the method, the quality of the concrete structures will be ensured using dedicated hardware shortly.

关键词： crack detection deep learning convolution neural network image segmentation CNN system image processing image classification

来源：评论

学校读者我要写书评

暂无评论

Dual-Branch and Multi-Scale Information Complementary Network for Hard Exudates Segmentation in Color Fundus images 2

Dual-Branch and Multi-Scale Information Complementary Networ...

引用

2nd International conference on machine vision, image processing and Imaging Technology, MVIPIT 2024

作者： Xu, Pengdao Zhang, Lin Zhao, Heng Wang, Yingjie Liu, Jiaoli Liu, Hui School of Information and Control Engineering China University of Mining and Technology Xuzhou China

ISBN: (纸本)9798331543037

Diabetic Retinopathy (DR) is known as one type of complication of long-term diabetes resulting in severe deterioration of vision, even blindness. Hard exudates (HE) are a type of diabetic macular edema and a prevalent cause of vision impairment for DR patients. Detecting HE is essential for DR diagnosis. Herein, a method for detecting HE with a dual-branch multi-scale approach is proposed. Specifically, the model consists of two branches: the main branch is designed to identify prominent features of the lesions, while the auxiliary branch utilizes a standard encoder and a ResNet50 encoder to identify deep features of the lesions, with two different resolution images serving as their inputs. Considering the variation in sizes and shapes, a multi-scale attention mechanism is integrated into the skip connections of the main branch, enabling the model to segment lesions of different scales. The feature maps finally obtained from both branches are aggregated before reaching the decoder, allowing the capture of contextual information from fundus images. Experiments on the IDRiD, E-Ophtha and DDR datasets show that the Dice of our method reached 74.53%, 68.87% and 59.40%, the IoU reached 59.40%, 52.52% and 42.25%, and the AUC reached 80.58%, 83.88% and 74.79% 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

Multi-level image detail enhancement based on guided filtering

Multi-level image detail enhancement based on guided filteri...

引用

2023 International conference on Algorithm, Imaging processing, and machine vision, AIPMV 2023

作者： Tian, Xiangrui Jia, Yinjun Xu, Tong Yin, Jie Chen, Yihe Mao, Jiansen College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing210016 China Beijing Changfeng Kewei Photoelectric Technology CO. LTD. Beijing100141 China

ISBN: (纸本)9781510672444

image blur and detail information loss are caused by various factors such as imaging environment and hardware performance, therefore a multi-level image detail enhancement method based on guided filtering is proposed. Firstly, the input image is iteratively filtered by using the guided filter, to obtain background images with different smoothness;then the background image is subtracted from the original image to obtain detail images with different levels;finally, a dynamic saturation function is used to adjust the weights of detail images, which are superimposed with the original image to obtain the enhanced image. The proposed method is compared with the existing enhancement algorithms using open dataset. The experimental results show that, compared with other enhancement methods, the proposed method in this paper achieves a better enhancement effect, the enhanced image has clear edges, and the visual effect is suitable. Compared with other methods, the objective indicators of information entropy, average gradient, and spatial frequency are improved on average. 1.39%, 27.9%, and 19.3%. © 2024 SPIE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

A Belief Theory Based Instance Selection Scheme for Label Noise and Outlier Detection from Breast Cancer Data 8th

A Belief Theory Based Instance Selection Scheme for Label No...

引用

8th International conference on Computer vision and image processing (CVIP)

作者： Faziludeen, Shameer Sankaran, Praveen Natl Inst Technol Calicut Kozhikode Kerala India

ISBN: (纸本)9783031581731;9783031581748

In case of real datasets, the likelihood of the training data being corrupted with training label noise and outliers arises. Certain classification algorithms including support vector machine (SVM) is sensitive to noise and outlier samples which can degrade their performance. Belief theory which involves an extension of the general probabilistic model and utilises combination rules for information fusion has found good use in the realm of classifiers. In this paper, we propose a belief theory based instance selection (BIS) scheme using the k nearest neighbours (KNN) algorithm for removing outlier and noise samples prior to SVM training to increase classification performance for breast cancer FNAC (Fine needle aspiration cytology) image data features. Our algorithm is tested on the WBCD database from the UCI machine learning repository which contains FNAC image data features. Performance evaluation is done by considering accuracy and confusion matrix measures. Effect of noise is assessed by testing on the datasets after contaminating the training data by random mislabelling. Results are compared with the conventional SVM algorithm for both the noisy and noiseless datasets. The proposed BIS scheme is shown to improve the performance of the SVM classifier considerably under noisy conditions.

关键词： Support vector machine belief theory Dempster Shafer theory evidential k nearest neighbours k nearest neighbours breast cancer histopathology FNAC image

来源：评论

学校读者我要写书评

暂无评论

Advanced Multi-Dimensional Feature Fusion Attention Module 24

Advanced Multi-Dimensional Feature Fusion Attention Module

引用

6th International conference on image processing and machine vision (IPMV)

作者： Shi, Yi Li, Zhe North Eastern Univ Shenyang Peoples R China

ISBN: (纸本)9798400708473

Recent study has emphasized the importance of establish multidimensional information dependencies between weight vectors and input feature maps, in the process of calculating attention. However, although existing networks establish the connection from different perspectives, the connection presented is relatively limited, and the network's differentiation between important and non-important information is insufficiency, which inevitably leads to effective information loss. This article studies an efficient channel attention mechanism that can fuse multi-dimensional feature information, implement the interaction of channel and spatial position feature from both independent channels and global cross channels dimensions, and able to expand important information while suppress unimportant information. We propose the SW-SE block, which assigns the spatial position information of the cross channel to the process of calculating channel attention, strengthens information exchange between multiple channels, establishes closer connections, and obtains channel weight vectors with better expressiveness while greatly enhancing feature sampling ability. We have conducted ablation experiments on various mainstream network structures, and have achieved fine results in multiple aspects, e.g., classification, object detection and visualization. We reached 3.12% and 1.41% top-1 accuracy growth based on Resnet 50/100 on CIFAR10/100 respectively, and 4.01% on light weight network, along with 8.57% increased on AP75 for object detection on PASCAL VOC2007/2012, with only a small number of parameters and computation time increased.

关键词： Attention CNN Network image representations Feature Fusion

来源：评论

学校读者我要写书评

暂无评论

Round fruit picking system based on machine vision

Round fruit picking system based on machine vision

引用

2024 International conference on Industrial Robotics and Advanced Manufacturing Technology, IRAMT 2024

作者： Fang, Xiumei Zhu, Haiyang Li, Sanyan Zhang, Qilong Department of Robotics Chengdu Jincheng College Sichuan Chengdu611731 China Houtian Technology Co. Sichuan Meishan620564 China

Traditional fruit quality selection mainly relies on manual labor, which is costly and time-consuming, and the results are difficult to meet the accuracy requirements. To solve this problem, this paper proposes a fruit-picking system based on machine vision technology using MATLAB as a software tool. It takes round fruits as the research object, introducing Zhang’s camera calibration method, making the target picture reach the ideal state through image pre-processing, such as edging processing, filtering and denoising, binary processing, size eigenvalue extraction, etc. Then, the fruit size grade is evaluated by using the Sobel edge detection algorithm. The fruit color grade is evaluated using the HSV detection algorithm to assess the fruit color grade, and a feature extraction method is used to assess the relative score of the defect degree. Finally, a weighted composite score is used to evaluate the fruit quality grade. This paper also designed a visualized GUI interface. The results prove that the system can accurately and quickly perform fruit selection and quality rating. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： machine vision

来源：评论

学校读者我要写书评

暂无评论

A Multi-scale Framework towards Human-machine Friendly Remote Sensing image Coding 6

A Multi-scale Framework towards Human-Machine Friendly Remot...

引用

6th ACM International conference on Multimedia in Asia, MMAsia 2024

作者： He, Yingkai Zhang, Zhen Xiao, Jing School of Computer Science Wuhan University Hubei Province Wuhan City China

ISBN: (纸本)9798400712739

With the increasing availability of remote sensing data and the development of machine learning-based collaborative interpretation techniques, remote sensing image transmission needs to serve both human and machine vision, in addition to achieving high-efficiency compression. However, existing compression methods that are optimized for pixel-level representation often suffer from performance degradation when confronted with downstream machine analysis *** address this issue, we propose a feature-domain-optimized, human-machine friendly remote sensing image compression framework. We design a compact multi-scale feature extractor to transform images into a feature domain representation, and then compress the compact feature for efficient transmission. During the decoding process, the compressed feature is directly used for machine analysis, which avoids the trade-off between human and machine vision requirements. To reconstruct visually pleasing images, we exploit the synergy between tasks and enhance the image reconstruction process with features from high-level *** results on the AID and NWPU-RESISC45 datasets demonstrate that our proposed method outperforms existing compression techniques in terms of analytical performance, while maintaining equivalent visual effects. This work highlights the importance of designing compression methods that are tailored to the needs of both human interpreters and machine analysis tasks in the context of remote sensing image processing. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： image compression

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 << < 21 22 23 24 25 26 27 28 29 30 > >>

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：