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

13,266 篇 会议
209 篇 期刊文献
183 册 图书
3 篇 学位论文
1 篇 资讯

馆藏范围

13,662 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

7,045 篇 工学
- 4,663 篇 计算机科学与技术...
- 2,299 篇 软件工程
- 2,127 篇 电气工程
- 1,341 篇 信息与通信工程
- 867 篇 控制科学与工程
- 697 篇 光学工程
- 499 篇 生物医学工程（可授...
- 476 篇 电子科学与技术（可...
- 469 篇 机械工程
- 459 篇 仪器科学与技术
- 331 篇 生物工程
- 241 篇 测绘科学与技术
- 168 篇 材料科学与工程（可...
- 160 篇 航空宇航科学与技...
- 147 篇 交通运输工程
- 107 篇 安全科学与工程
- 92 篇 化学工程与技术
3,499 篇 理学
- 2,413 篇 物理学
- 937 篇 数学
- 388 篇 生物学
- 249 篇 系统科学
- 237 篇 统计学（可授理学、...
- 122 篇 化学
1,507 篇 医学
- 1,336 篇 临床医学
- 211 篇 特种医学
- 170 篇 基础医学(可授医学...
- 111 篇 药学(可授医学、理...
723 篇 管理学
- 436 篇 管理科学与工程(可...
- 311 篇 图书情报与档案管...
- 89 篇 工商管理
61 篇 法学
59 篇 农学
31 篇 教育学
29 篇 经济学
28 篇 文学
20 篇 军事学
17 篇 艺术学
1 篇 哲学

主题

2,765 篇 image processing
1,435 篇 image segmentati...
1,171 篇 signal processin...
626 篇 feature extracti...
624 篇 cameras
587 篇 image edge detec...
564 篇 signal processin...
492 篇 image coding
486 篇 image reconstruc...
480 篇 real-time system...
395 篇 algorithm design...
346 篇 image color anal...
317 篇 deep learning
314 篇 image enhancemen...
313 篇 image analysis
309 篇 pixel
306 篇 real time system...
304 篇 computer archite...
298 篇 object detection
291 篇 hardware

机构

23 篇 signal and image...
20 篇 samara national ...
14 篇 school of electr...
11 篇 samara national ...
11 篇 purdue univ sch ...
11 篇 univ texas san a...
11 篇 department of el...
11 篇 school of electr...
10 篇 center for signa...
9 篇 information syst...
9 篇 institute of ima...
9 篇 university of to...
9 篇 tongji universit...
9 篇 samara national ...
8 篇 university of ch...
8 篇 electrical compu...
8 篇 image processing...
8 篇 information syst...
7 篇 school of electr...
7 篇 department of ma...

作者

19 篇 anon
13 篇 de-shuang huang
13 篇 jagdish chand ba...
11 篇 p. pirsch
10 篇 jie yang
10 篇 panetta karen
10 篇 j.m. mendel
10 篇 r. chellappa
9 篇 c.-c.j. kuo
9 篇 a. ortega
8 篇 frank hannig
8 篇 hannig frank
8 篇 ilias maglogiann...
7 篇 miller jwv
7 篇 busch christoph
7 篇 semenishchev e.
7 篇 zelensky a.
7 篇 bovik alan c.
7 篇 jerry m. mendel
7 篇 kupriyanov a.v.

语言

13,113 篇 英文
459 篇 其他
87 篇 中文
20 篇 土耳其文
3 篇 葡萄牙文
2 篇 西班牙文
2 篇 俄文
1 篇 法文

检索条件"任意字段=Conference on Image Processing - Algorithms and Systems IV"

共 13662 条记录，以下是1301-1310 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：

Learning Staged Trees from Incomplete Data 12

Learning Staged Trees from Incomplete Data

引用

12th International conference on Probabilistic Graphical Models, PGM 2024

作者： Carter, Jack Storror Leonelli, Manuele Riccomagno, Eva Varando, Gherardo Dipartimento di Matematica Università degli Studi di Genova Genova Italy School of Science and Technology IE University Madrid Spain Image Processing Laboratory Universitat de València València Spain

Staged trees are probabilistic graphical models capable of representing any class of non-symmetric independence via a coloring of their vertices. Several structural learning routines have been defined and implemented to learn staged trees from data, under the frequentist or Bayesian paradigm. They assume a data set has been observed fully and, in practice, observations with missing entries are either dropped or imputed before learning the model. Here, we introduce the first algorithms for staged trees that handle missingness within the learning of the model. To this end, we characterize the likelihood of staged tree models in the presence of missing data and discuss pseudo-likelihoods that approximate it. A structural expectation-maximization algorithm estimating the model directly from the full likelihood is also implemented and evaluated. A computational experiment showcases the performance of the novel learning algorithms, demonstrating that it is feasible to account for different missingness patterns when learning staged trees. © 2024 J.S. Carter, M. Leonelli, E. Riccomagno & G. Varando.

关键词： Expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

FULL POLARIMETRIC TIME SERIES image ANALYSIS FOR CROP TYPE MAPPING 6

FULL POLARIMETRIC TIME SERIES IMAGE ANALYSIS FOR CROP TYPE M...

引用

ISPRS GeoSpatial conference / Joint 6th Sensors and Models in Photogrammetry and Remote Sensing conference (SMPR) / 4th Geospatial Information Research (GIResearch) conference

作者： Noroozi, H. Hasanlou, M. Univ Tehran Sch Surveying & Geospatial Engn Coll Engn Tehran Iran

Crop information and quality are not only fundamental for experts using spatial decision support systems but also have many applications in irrigation management, economic analysis for import or export, food safety, and achieving sustainable agriculture. Remote sensing is a cheap and fast way of reaching this goal. Full polarimetric SAR unlike optical sensors is an all-weather system providing geometrical and physical properties of the earth's surface events. Due to the dynamic changes in crop properties through their phenological stages, crop type mapping has been challenging. As a result, accurate, reliable, and cost-effective crop type mapping using minimum data and processing has been the goal of the remote sensing and precision agriculture community. In this study, a new method based on time series analysis of full polarimetric SAR data combined with radar indices, polarimetric decompositions followed by the three as extracted from H/A/a decomposition, and unsupervised H/a/Wishart classification bands as features generated from only 5 dates of RADARSAT CONSTELLATION MISSION 2 data were used for classification of crops. Applying random forest and cat boost algorithm as classifiers an accuracy of 87.4% and 75% was respectively achieved. indicating that both algorithms have promising results. Although the random forest algorithm had better results, the cat boost algorithm had less noise in each field and more homogenous farms were detected.

关键词： Crop type RADARSAT 2 Polarimetry Machine learning Random Forest Cat Boost

来源：评论

学校读者我要写书评

暂无评论

A New Perspective on Subset Partitioning in Ensemble Learning

A New Perspective on Subset Partitioning in Ensemble Learnin...

引用

Innovations in Intelligent systems and Applications conference

作者： Meerim Kubatova Bora Isikoglu Aydin Cetin Computer Engineering Department Gazi University Graduate School of Natural and Applied Sciences Ankara Türkiye HAVELSAN Inc. Ankara Türkiye

ISBN: (数字)9798350379433

ISBN: (纸本)9798350379440

Artificial intelligence technology is indispensable to today's intelligent systems. Ensemble learning, one of the machine learning techniques that is a sub-branch of AI, was studied in this experimental research. Ensemble Learning is created to overcome the individual limitations of existing models and to combine powers for a more optimized final model by working all together. The study is focused on improving the existing Ensemble Learning approach. The innovative aspect of the study is the introduction of a vertical (feature-based) subsetting technique instead of the horizontal (sample-based) subsetting technique used in the process of preparing the subsets for training different weak learners using homogeneous or heterogeneous learning algorithms. Learning from different features allows each model to learn different patterns from one another, therefore, enhancing the ensemble model's evaluation abilities. The proposed approach has been tested on a process that utilizes a combination of a preprocessing step that uses the vertical subsetting method and a training step that brings out the ensemble model using different (heterogeneous) learning algorithms. The obtained results of the experimental study have shown positive effects in terms of F 1 -Score and can contribute to the literature. Ensemble learning, particularly with the introduction of novel techniques like vertical subsetting, opens the door for new experimental studies that may be initiated for the development of intelligent systems across multiple fields such as financial forecasting, weather forecasting, medical diagnosis, marketing, e-commerce, cybersecurity, natural language processing, image recognition, and autonomous vehicles.

关键词： Training Technological innovation image recognition Weather forecasting Prediction algorithms Natural language processing Ensemble learning Medical diagnosis Intelligent systems Forecasting

来源：评论

学校读者我要写书评

暂无评论

CLEAR: An Efficient Traffic Sign Recognition Technique for Cyber-Physical Transportation systems 15

CLEAR: An Efficient Traffic Sign Recognition Technique for C...

引用

IEEE/ACM 15th International conference on Utility and Cloud Computing (UCC) / 9th International conference on Big Data Computing, Applications and Technologies (BDCAT)

作者： Rai, Meghna Khosla, Bhawna Dhawan, Yash Kharotia, Himanshi Kumar, Neeraj Bandi, Ajay Thapar Inst Engn & Technol Dept Comp Sci & Engn Patiala Punjab India Northwest Missouri State Univ Maryville MO USA

ISBN: (纸本)9781665460873

In this modern era, the popularity of autonomous systems has increased manifold because they are replacing people in various jobs and are expected to become the backbone of modern society. Specifically, self-driving vehicles and robots are gaining popularity in a wide range of applications. However, traffic sign detection, a critical component of intelligent transportation systems, remains quite challenging since it needs to be done quickly, with high precision, and with high dependability. A fast, real-time, robust automatic traffic sign detection and recognition can support and relieve the driver and significantly increase driving safety and comfort. Out of many algorithms and frameworks available for traffic sign identification, i.e., object detection, one of the most popular ones is You Only Look Once (YOLO) since it provides accurate results with minimal background errors in most real-time processing tasks and has excellent learning capabilities. Motivated by this, this research article provides a novel framework, CLEAR, for traffic sign identification in adverse climate conditions using YOLOv5. We compare different models' speed, accuracy, and other metrics on a Traffic Sign Dataset obtained from the Open image Dataset V6. Experimental results demonstrated that the proposed CLEAR model achieved the best performance with a Mean Average Precision of 0.73392 and Recall of 0.74194 compared to the existing schemes.

关键词： YOLO Traffic Signs Autonomous Vehicles Object Detection image Classification Computer Vision Deep Learning Real-Time Detection

来源：评论

学校读者我要写书评

暂无评论

Error Diffusion based Feedforward Height Control for Inkjet 3D Printing

Error Diffusion based Feedforward Height Control for Inkjet ...

引用

IEEE/ASME International conference on Advanced Intelligent Mechatronics (AIM)

作者： Wu, Yumeng Chiu, George Purdue Univ Coll Engn Sch Mech Engn W Lafayette IN 47907 USA

ISBN: (纸本)9781665476331

Inkjet 3D printing is capable of building highresolution components layer by layer with polymer-based materials that can also include functional components. Currently, most inkjet 3D printers are operated with prescribed layer structures to achieve a desired geometry and, in particular, a desired heigh profile. This often leads to discrepancy between target geometry and actual products. This article presents a framework to leverage halftoning processes in inkjet printing of images to inkjet 3D printing to improve geometric integrity and specifically a more precise height profile. By using the existing imaging pipeline, this framework requires no modification to current hardware. Halftone is a fundamental step in imaging pipeline for all digital printing systems. Error diffusion is one of the most common and widely used halftone algorithms. In this work, we will use two different error diffusion kernels, the 2x3 Floyd and Steinberg (FS) kernel and the 3x5 Jarvis, Judice and Ninke (JJN) kernel to demonstrate the feasibility and improve height profile control of an inkjet 3D printer using UV curable inks. The current implementation operates in a feedforward manner using a previously validated 2D height profile model to provide heigh estimation after the deposition of each layer. Two 3D geometry samples are printed using the proposed approach. Consistent RMS height profile errors and standard deviations from different samples demonstrated the effectiveness of the proposed approach to improve height profile tracking in inkjet 3D printing.

关键词： Digital Printing Additive Manufacturing Process Modeling Three-Dimensional Printing Process Control image processing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multilingual image Captioning: Integrating Text-to-Speech Translation and Sentiment Analysis

Enhanced Multilingual Image Captioning: Integrating Text-to-...

引用

Innovative Computing, Intelligent Communication and Smart Electrical systems (ICSES), International conference on

作者： Tanuja Konda Reddy S Veeksha C.R. Kavitha Department of CSE Amrita School of Computing Bengaluru India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

The aim of this project is to create a system that will improve the way we interact with text and images by using the capabilities of computer vision and natural language processing. The main purpose of using this system to generate human-readable image captions is to train a model that can accurately describe an image's contents. The project extends the functionality of the image captioning system by adding language translation inorder to give a multilingual support. The use of a few pre-trained models will enable users with varying language backgrounds use this system to acquire captions in different target languages. This involves integrating language translation techniques into the system and training different models for every target language. Further we extend the project by working in the field of sentiment analysis by identifying the sentiment (positive, negative, or neutral) of captions by examining text and images. For a better understanding of the emotional tone of the information, the system combines CNNs with natural language processing (NLP) algorithms for image analysis and text analysis.

关键词： Training Sentiment analysis Computer vision Translation Text analysis image analysis Multilingual Text to speech Labeling Creativity

来源：评论

学校读者我要写书评

暂无评论

A Comparison between AttnGAN and DF GAN: Text to image Synthesis 3

A Comparison between AttnGAN and DF GAN: Text to Image Synth...

引用

3rd International conference on Signal processing and Communication (ICPSC)

作者： Sumi, Philo Sindhuja, S. Sureshkumar, S. Bannari Amman Inst Technol Dept Comp Sci & Engn Sathyamangalam India

ISBN: (纸本)9781665428644

Nowadays conversion from text to high resolution image is a challenging task due to its wide variety of application area. For text to image conversion almost all systems use Generative Adversarial Networks as the basic part of the system and GAN guarantees semantic consistency between the text input and the generated image output. In this paper we are comparing two algorithms that is used for generating image from text. The first algorithm is the AttnGAN and the second one is the DF-GAN. AttnGAN builds on top of StackGAN by using attention network which allows it to capture word level information along with the broader sentence level information. The second algorithm is the DF-GAN, which uses single generator and discriminator model to synthesize high resolution images and also uses Matching-Aware Gradient Penalty (MA-GP) to get real images with real description. The model contains a Deep text-image Fusion Block ( DFBlock) to generate image features from text. Both algorithms work efficiently for image generation from text but DF-GAN generates the perfect output than AttnGAN. The AttnGAN always focus on the textual part to generate output image but DF-GAN also focuses on background of image.

关键词： AttnGAN DF GAN BLSTM CNN

来源：评论

学校读者我要写书评

暂无评论

Human Pose Estimation Based on Multi-Level Feature Fusion

Human Pose Estimation Based on Multi-Level Feature Fusion

引用

International conference on Vision, image and Signal processing (ICVISP)

作者： Hewei Yu Zhuoheng Li Yanhua Mou Guangzhou Xinhua University Dongguan China South China University of Technology Guangzhou China Liuzhou Institute of Technology Liuzhou China

ISBN: (数字)9798331541460

ISBN: (纸本)9798331541477

We propose a human pose estimation algorithm based on multi-level feature fusion module. To enhance information transmission and feature fusion among different feature levels, we design a multi-level feature fusion structure. Further more, we use a multi-level feature fusion module based on a parallel multi-level feature fusion structure to improve the estimation network's ability to process multi-scale targets. The new network, built upon stacked multi-level feature fusion modules, exhibits strong capabilities in learning semantic information, extracting and fusing multi-scale features. When applied to human pose estimation tasks, it can effectively generate high-precision, high-resolution heatmaps for predicting human key points. This algorithm improves the AP(Average Precision) by 1.3 compared to Simple Baselines on the COCO dataset and enhances the PCKh@0.5 metric by 0.2 compared to Simple Baselines on the MPII dataset. The experiments demonstrate the effectiveness of the proposed algorithm.

关键词： Measurement Heating systems Pose estimation Semantics Neural networks Signal processing algorithms Information processing Feature extraction Prediction algorithms Resource management

来源：评论

学校读者我要写书评

暂无评论

Design of computing granularity configurable processor based on RISC-V extended instruction 16

Design of computing granularity configurable processor based...

引用

16th IEEE International conference on Solid-State and Integrated Circuit Technology, ICSICT 2022

作者： He, Bin Yu, Ning-Mei Xu, Meng Wang, Xing-Jia Xi'an University of Technology School of Automation and Information Engineering Xi'an710000 China

ISBN: (数字)9781665469067

ISBN: (纸本)9781665469067

Aiming at the problems of long operation time and poor flexibility of embedded processor, this paper proposes a structure of configurable execution unit based on RISC-V extended instruction set for computing granularity. The structure sets up basic parallel computing units and configuration registers, which can realize a large number of parallel operations such as multiplication, addition, or higher abstractions similar to convolutional neural networks by software configuration. This paper completed the design of this structure and integrated it into a four-stage pipelined RISC-V processor. The white blood cell images collected by lensless system are used to test various image algorithms. The experimental results show that the processor speed designed in this paper is 5.95 times to 22.21 times higher than that of the ordinary pipeline processor, and the number of instructions required is reduced by 1.16 times to 7.49 times. Therefore, the processor has a certain improvement in processing speed and flexibility, which is of great significance for the implementation of various algorithms in embedded systems. © 2022 IEEE.

关键词： Pipeline processing systems

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of image processing and Different Machine Learning Models in Classifying Local Soybean Varieties in the Philippines

Effectiveness of Image Processing and Different Machine Lear...

引用

IEEE conference on systems, Process & Control (ICSPC)

作者： Isaac Angelo M. Dioses Romero Dante Salum Desiray Nayga Mark Joseph Asuncion Jesusimo L. Dioses Wendell M. Castillo School of Information Technology MAPUA University Makati Campus Metro Manila Makati Philippines College of Computing Studies Information and Communication Technology Isabela State University San Fabian Echague Isabela Philippines

ISBN: (数字)9798350391398

ISBN: (纸本)9798350391404

Deceptive providers offering inferior products threaten the integrity of soybean exportation and product quality. To uphold fair trade standards and protect consumer rights, it is essential to classify and trace different soybean varieties accurately. Implementing stringent legislation and reliable technology for crop origin identification is crucial in maintaining order in the soybean trading market. This study uses artificial intelligence, specifically machine learning, image processing, and computer vision, to develop a standard model for soybean classification. Researchers collected two bags of soybeans from CVRC Cagayan at Ilagan Isabela, resulting in a dataset of 1562 soybean images, with 810 images of PSB SY2 and 752 images of CL1 Soy. The study employed Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) algorithms to create models for classifying and predicting soybean varieties. The SVM model achieved an accuracy of $\mathbf{8 8. 2 \%}$, while the KNN model, using the FINE KNN preset, outperformed with an accuracy of $\mathbf{9 4. 4 \%}$. Although the KNN algorithm exhibited slower training speed and time, it demonstrated superior accuracy over the SVM model, as evidenced by its confusion matrix. Feature selection using the MRMR algorithm identified perimeter and equivalent diameter as the most significant features for soybean classification, while minor axis length was deemed the least important. To improve the precision and dependability of soybean variety classification and safeguard customer interests, this research emphasizes the potential of machine learning approaches in conjunction with image processing and morphology feature extraction.

关键词： Support vector machines Training Accuracy Machine learning algorithms Machine learning Nearest neighbor methods Predictive models Prediction algorithms Classification algorithms Standards

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 << < 127 128 129 130 131 132 133 134 135 136 > >>

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：