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

4,618 篇 会议
499 册 图书
66 篇 期刊文献

馆藏范围

5,182 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

3,388 篇 工学
- 2,748 篇 计算机科学与技术...
- 1,819 篇 软件工程
- 728 篇 信息与通信工程
- 723 篇 光学工程
- 668 篇 电气工程
- 415 篇 生物工程
- 363 篇 控制科学与工程
- 348 篇 生物医学工程（可授...
- 239 篇 机械工程
- 228 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
- 117 篇 安全科学与工程
- 96 篇 交通运输工程
- 91 篇 材料科学与工程（可...
- 67 篇 建筑学
- 57 篇 土木工程
1,684 篇 理学
- 928 篇 物理学
- 725 篇 数学
- 452 篇 生物学
- 204 篇 统计学（可授理学、...
- 119 篇 化学
- 57 篇 系统科学
490 篇 管理学
- 270 篇 图书情报与档案管...
- 242 篇 管理科学与工程(可...
- 79 篇 工商管理
438 篇 医学
- 417 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

820 篇 computer vision
625 篇 pattern recognit...
538 篇 image processing
355 篇 image processing...
348 篇 artificial intel...
336 篇 image segmentati...
276 篇 feature extracti...
203 篇 image recognitio...
176 篇 deep learning
155 篇 computer graphic...
150 篇 computer imaging...
139 篇 face recognition
128 篇 machine learning
121 篇 object recogniti...
120 篇 convolutional ne...
115 篇 object detection
115 篇 image analysis
108 篇 information syst...
105 篇 cameras
105 篇 shape

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...
11 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 tongji universit...
8 篇 erasmus mc - uni...
8 篇 beijing institut...
8 篇 tencent jarvis l...

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
9 篇 paul scheunders
9 篇 h. bischof
9 篇 jie yang
9 篇 stéphane cotin
9 篇 dan popescu
9 篇 mohamed kamel
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

4,760 篇 英文
402 篇 其他
70 篇 中文

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

共 5183 条记录，以下是841-850 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：

Basic design for the implementation of automatic surveillance system on helmet detection 4

Basic design for the implementation of automatic surveillanc...

引用

4th international conference on Artificial Intelligence and Speech Technology, AIST 2022

作者： Dath, Mogalraj Kushal Rakhra, Manik Singh, Dalwinder Singh, Arun Banala, Rajesh Lovely Professional University Department of Computer Science and Engineering Phagwara India

ISBN: (纸本)9781665499026

Deep learning has lately received acclaim for its success in certain fields, such as digital image pattern recognition and feature extraction. these methods have been used by researchers to solve a variety of issues, such as the detection of traffic violations specifically for motorcycle riders who are not wearing helmets in video surveillance. In this paper, we proposed a basic implementation and design steps of detecting two-wheeler bike rider wearing helmet utilizing a compatible and faster deep learning approach known as Single Shot Detector (SSD) in Linux operating system. We used and created a customized dataset of images by taking screenshots of a surveillance video of CCTV from a legal source. the traffic police can use this system to monitor the vehicles passing through specific surveillance nodes. After further implementation, number plates of vehicles could automatically be logged in a database which may be helpful in narrowing down options during a crime investigation. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Concatenation-Based Convolutional Network

A Concatenation-Based Convolutional Network

引用

Robotics, Automation and Artificial Intelligence (RAAI), IEEE international conference on

作者： Shenson Joseph Ashok Gadi Parthi Durgaraman Maruthavanan Prema Kumar Veerapaneni Vivekananda Jayaram Balakrishna Pothineni University Of North Dakota Houston Texas USA

ISBN: (数字)9798331520038

ISBN: (纸本)9798331520045

Convolutional Neural Networks (CNNs) excel in image recognition and object detection but face challenges like the vanishing gradient problem in deeper networks. ResNets address this with skip connections, while ConcatNet introduces a novel approach inspired by DenseNets, connecting each layer to all subsequent layers via concatenation. this design enhances information flow, learning efficiency, and feature reuse. ConcatNet outperforms in object recognition, achieves high accuracy with minimal data augmentation, and excels in semantic segmentation. It optimizes memory usage and shows shorter training times per epoch, with full potential realized over longer training periods. ConcatNet's innovative architecture boosts performance in traditional tasks and opens new possibilities for computer vision applications. Future research may explore hybrid models combining ConcatNet's dense connectivity with ResNet's skip connections for improved training efficiency and robustness.

关键词： Training computer vision image recognition Semantic segmentation Memory management Object detection Robustness Convolutional neural networks Object recognition Optimization

来源：评论

学校读者我要写书评

暂无评论

A machine vision-based batch measurement system for workpiece dimensions 24

A machine vision-based batch measurement system for workpiec...

引用

Proceedings of the 2024 7th international conference on Artificial Intelligence and pattern recognition

作者： Wanyu Deng Zhaojie Li Faculty of Computer Science Xi'an University of Posts & Telecommunications Xi'an shaanxi China

ISBN: (纸本)9798400717178

Industrial part detection is a critical part of the product manufacturing process. the measurement of product dimensions is a crucial aspect of the control of product quality. In response to the existing workpiece size measurement process, which is characterised by slow detection speeds, low accuracy, and high labour costs. A scheme for measuring the workpiece size based on machine vision is proposed, and an intuitive, lightweight measurement system is constructed. this solution organically combines image processing, edge extraction and template matching, first performing image pre-processing operations on the image to be detected, then obtaining the corresponding region of interest (ROI), and then a precise measurement can be derived. In order to enhance the efficacy of workpiece inspection and to facilitate subsequent reuse, the system offers the capacity for persistent storage of existing model templates. Following experimental verification, the system is capable of achieving rapid, one-click measurement of multiple targets and multiple geometric parameters of small workpiece, with an accuracy of 0.02mm, thus meeting the current enterprise's actual needs.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

CURL: Neural Curve Layers for Global image Enhancement 25

CURL: Neural Curve Layers for Global Image Enhancement

引用

25th international conference on pattern recognition (ICPR)

作者： Moran, Sean McDonagh, Steven Slabaugh, Gregory JP Morgan Chase & Co New York NY 10172 USA Huawei Noahs Ark Lab New York NY USA Queen Mary Univ London London England

ISBN: (纸本)9781728188089

We present a novel approach to adjust global i mage properties such as colour, saturation, and luminance using human-interpretable image enhancement curves, inspired by the Photoshop curves tool. Our method, dubbed neural CURve Layers (CURL), is designed as a multi-colour space neural retouching block trained jointly in three different colour spaces (HSV, CIELab, RGB) guided by a novel multi-colour space loss. the curves are fully differentiable and are trained end-to-end for different computer vision problems including photo enhancement (RGB-to-RGB) and as part of the image signal processing pipeline for image formation (RAW-to-RGB). To demonstrate the effectiveness of CURL we combine this global image transformation block with a pixel-level (local) image multi-scale encoder-decoder backbone network. In an extensive experimental evaluation we show that CURL produces stateof-the-art image quality versus recently proposed deep learning approaches in both objective and perceptual metrics, setting new state-of-the-art performance on multiple public datasets. Our code is publicly available at: https://***/sjmoran/CURL.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Banana Ripeness Identification and Classification Using Hybrid Models with RESNET-50, VGG-16 and Machine Learning Techniques 4th

Banana Ripeness Identification and Classification Using Hybr...

引用

4th international conference on Machine Intelligence and Signal processing, MISP 2022

作者： Mathew, Milan Bins Surya Manjunathan, G. Gokul, B. Mohana Ganesh, K. Sajidha, S.A. Nisha, V.M. School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India

ISBN: (纸本)9789819900848

For any fruit or vegetable consumers consider the ripeness of the item as one of the major indicators of its price and quality. Similarly, for bananas, the quality of the fruit is strongly associated with its ripeness and is a matter of concern for consumers, producers and traders of this fruit. this is because the ripeness of a fruit is associated with its taste, texture, and edibility which is important for any food. A manual method of classifying the bananas based on their ripeness is a tedious and impractical technique. this study aims to use modern day computer vision technologies to automatically identify and classify bananas based on their ripeness. We propose a hybrid model BanNet that aims to use a hybrid model that uses deep learning models like VGG-16 and ResNet-50 for feature extraction and a machine learning classifier to classify the banana based on its ripeness. the bananas will be classified into 4 categories—ripe, mid-ripe, overripe and unripe. the results are compared with other machine learning classifiers and another deep learning model used for feature extraction. the results reveal that the proposed system has a better overall recognition rate than the other techniques discussed. © 2023, the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Automatic image Caption Generation Using ResNet & Torch vision 4th

Automatic Image Caption Generation Using ResNet & Torch Visi...

引用

4th international conference on Machine Learning, image processing, Network Security and Data Sciences (MIND)

作者： Verma, Vijeta Saritha, Sri Khetwat Jain, Sweta Maulana Azad Natl Inst Technol Bhopal India

ISBN: (纸本)9783031243660;9783031243677

image captioning is a task through which a textual description can be generated that illustrated the action performed in the image. It is one of the most complicated research areas where only the machine learning approach can intervene. In the area of image captioning, a system should be intelligent enough to understand the semantic knowledge to recognize the object present in the image and the situation that evolves with it. In the proposed work an image captioning system has been generated using ResNet along with CNN and RNN. CNN is used as an encoder and RNN is used as a decoder. the system is able to infer the situation precisely for MSCOCO benchmark. the model has been trained with ResNet152 which effectively utilizes the layers and minimizes the computational time. ResNet skips the convolutional layers that solved the gradient exploding problem, that is why it is also known as skip connection. System perceived better Bilingual Evaluation Understudy (BLEU), METEOR, CIDEr, and Rouge score as compared to the previously implemented model. BLEU score has been evaluated with four parameters as B1, B2, B3 and B4 i.e., 0.57, 0.404, 0.279, 0.191 respectively. METEOR, CIDEr and Rouge have been depicted as 0.195, 0.396 and 0.6 respectively. Model has been better utilized to train the samples by reducing the size of the image and enhancing the brightness with pillow. System also uses the Torch vision library to enhance the model for better predicting the situation.

关键词： image captioning ResNet CNN RNN MSCOCO BLEU Machine learning

来源：评论

学校读者我要写书评

暂无评论

image Fusion Based on Memristive Neural Network

Image Fusion Based on Memristive Neural Network

引用

computer vision, image and Deep Learning (CVIDL), international conference on

作者： Huan Ding Tong Li Zelong Liu Ziwei Feng School of Electronic Engineering Tianjin University of Technology and Education Tianjin China

image fusion aims to integrate complementary information of images collected by multiple source channels into a single fusion image. It can extract the favorable information in each channel to the maximum extent and generate high quality image. this technology is widely used in various fields, among which the neural network is the most widely used. However, there are still many problems to be solved, such as the removal of redundant information and the retention of effective information. this paper proposes to add memristors on the basis of pulse coupled neural network to realize the adaptive change of neural network parameters, which breaks the shackles of traditional fixed parameters. this allows for better image fusion. For the two processing results, this paper combines the fusion image and grid sampling graph to analyze the processing effect. the results of pulse coupled neural network and memristive neural network were compared and analyzed from three aspects: information entropy, spatial frequency and average gradient. the experimental results show that the image fusion using memristive neural network is better and the resulting image is clearer. the feasibility and superiority of memristive neural network are verified.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Signal processing using AI Integrated Framework for Color and Drawing in Gesture recognition 5

Real-Time Signal Processing using AI Integrated Framework fo...

引用

5th international conference on Contemporary Computing and Informatics, IC3I 2022

作者： Lavania, Geerija Arya, Vivek Sharma, Neha Rashid, Mamoon Akram, Shaik Vaseem JECRC Artificial Intelligence & Data Science Department Rajasthan Jaipur India Dept of Electronics and Communication Engineering Haridwar India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India Vishwakarma University Department of Computer Engineering Pune India Uttaranchal Institute of Technology Uttaranchal University Dehradun India

ISBN: (纸本)9798350398267

In the realm of image processing and pattern recognition, writing with gestures in the air has grown in popularity and difficulty over the past few years. It contributes significantly to the creation of automation processes and can improve human-machine communication in a range of systems. Many studies focus on cutting-edge methods and techniques that will expedite processing while preserving a high level of identification accuracy. Internally, the area of computer vision considers object tracking to be crucial. Object tracking techniques are credited to modern computers, easy access to good-looking, affordable video cameras, and automated video analytics requirements. the video analysis technique generally consists of three fundamental steps: first, recognizing the object, second, tracking its movement from frame to frame, and third, assessing the behavior of that object. Each of the four takes into account a separate issue: choosing the best item representation, choosing the tracking function, purchasing the item, and tracking the item. Numerous real-world applications, such as autonomous monitoring, video identification, and vehicle navigation, depend heavily on object-tracking algorithms. this area is utilized by the research, which focuses on it to create a prospective text-to-text converter transition. this Research occasionally works as a freelance journalist. Your fingerprint will be tracked by a computer. the created text can be copied and used for a variety of things, including emails and SMS. For the deaf, it will be a potent means to establish this connection. By removing the need for writing, an efficient communication system decreases the use of the phone and laptop. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

GestureGuard: R-CNN for Sign Langauge

GestureGuard: R-CNN for Sign Langauge

引用

Intelligent Technologies (CONIT), international conference on

作者： T. Sethukarasi Anshika Sundararajan S Janavi Computer Science and Engineering R.M.K Engineering College Thiruvallur India

ISBN: (数字)9798350349900

ISBN: (纸本)9798350349917

this paper introduces an innovative system designed to assist individuals with vocal and hearing disabilities by enhancing sign language recognition and converting sign language into text. the project utilizes computer vision techniques and a Region based Convolutional Neural Network (RCNN) model to capture and interpret sign language gestures in real-time. Each frame of the gesture is captured through webcam and the features within the specified region marked by region of interest (ROI) are fed to the two-layer algorithm which comprises of convolution layers and pooling layers. Further to convert from text to sign, Natural Language Toolkit (NLTK) and TextRank algorithm are utilized to condense the sentences which eases the conversion. By tilizing an image-based approach, a user-friendly approach can be deployed easily even on the resource-constrained systems.

关键词： Sign language computer vision Webcams Text recognition Convolution Computational modeling Natural languages

来源：评论

学校读者我要写书评

暂无评论

A Fast Line and Ellipse Detection on High Resolution images 17th

A Fast Line and Ellipse Detection on High Resolution Image...

引用

17th Chinese conference on image and Graphics Technologies and Applications, IGTA 2022

作者： Liu, Limin Li, Dingzhe Li, Zhaoxi Meng, Cai The Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou510006 China Image Processing Center Beijing University of Aeronautics and Astronautics Beijing100191 China Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing100083 China

ISBN: (纸本)9789811950957

Line and ellipse are important image features in pattern recognition and computer vision. Many methods have been developed to extract line or ellipse in images separately but few try to detect them simultaneously. In this paper, a novel fast line and ellipse detection (FLED) method is proposed to detect line and ellipse simultaneously, even in high resolution images. At first, a detection framework (Pre-SGV) for high detection speed is proposed, which explicitly decomposes the detection into precalculate, segment, grouping, validation phases. Secondly, a simple but efficient algorithm is designed to segment the edges into line or arc candidates. thirdly, the grouping constraints and fitting methods are further improved. Finally, validation are conducted to exclude erroneous detection. Experiments on synthetic images and real image dataset show that the proposed method, FLED, can robustly detect lines and ellipses fast and efficiently, especially for high resolution image (e.g. remote sensing image, the scanning image). © 2022, the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： pattern recognition

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 << < 81 82 83 84 85 86 87 88 89 90 > >>

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：