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

13,311 篇 会议
220 篇 期刊文献
183 册 图书
3 篇 学位论文
1 篇 资讯

馆藏范围

13,718 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

7,077 篇 工学
- 4,689 篇 计算机科学与技术...
- 2,310 篇 软件工程
- 2,133 篇 电气工程
- 1,354 篇 信息与通信工程
- 889 篇 控制科学与工程
- 697 篇 光学工程
- 504 篇 生物医学工程（可授...
- 480 篇 电子科学与技术（可...
- 474 篇 机械工程
- 466 篇 仪器科学与技术
- 336 篇 生物工程
- 245 篇 测绘科学与技术
- 172 篇 材料科学与工程（可...
- 162 篇 航空宇航科学与技...
- 149 篇 交通运输工程
- 109 篇 安全科学与工程
- 95 篇 网络空间安全
- 94 篇 化学工程与技术
3,512 篇 理学
- 2,418 篇 物理学
- 944 篇 数学
- 392 篇 生物学
- 249 篇 系统科学
- 241 篇 统计学（可授理学、...
- 125 篇 化学
1,514 篇 医学
- 1,340 篇 临床医学
- 212 篇 特种医学
- 171 篇 基础医学(可授医学...
- 111 篇 药学(可授医学、理...
733 篇 管理学
- 442 篇 管理科学与工程(可...
- 314 篇 图书情报与档案管...
63 篇 法学
63 篇 农学
31 篇 教育学
30 篇 经济学
29 篇 文学
20 篇 军事学
17 篇 艺术学
1 篇 哲学

主题

2,783 篇 image processing
1,435 篇 image segmentati...
1,169 篇 signal processin...
630 篇 feature extracti...
620 篇 cameras
588 篇 image edge detec...
567 篇 signal processin...
494 篇 image reconstruc...
491 篇 image coding
486 篇 real-time system...
399 篇 algorithm design...
354 篇 image color anal...
322 篇 deep learning
315 篇 image enhancemen...
309 篇 pixel
306 篇 real time system...
306 篇 image analysis
303 篇 computer archite...
302 篇 hardware
300 篇 object detection

机构

22 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 samara national ...
10 篇 center for signa...
9 篇 information syst...
9 篇 institute of ima...
9 篇 university of to...
9 篇 tongji universit...
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
8 篇 frank hannig
8 篇 hannig frank
8 篇 ilias maglogiann...
8 篇 egiazarian karen
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

12,985 篇 英文
644 篇 其他
99 篇 中文
19 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 13718 条记录，以下是701-710 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：

processing of Analyzed Textual Information to a Meaningful Structure

Processing of Analyzed Textual Information to a Meaningful S...

引用

International Russian Automation conference, RusAutoCon 2022

作者： Semenov, R.E. MIREA – Russian Technological University 78 Vernadskogo Ave. Moscow119454 Russia

ISBN: (纸本)9783031223105

The results of studies of the morphological analysis of the text are demonstrated. Application of the technology of automatic processing of Russian-language texts to determine the parts of speech presented in the digital image. Definition of significant and non-essential information in the text. Identification and construction of a concept for implementation into an intelligent automated text recognition and analysis system. The correspondence of each word of the text to a certain part of speech according to a predetermined structure. The automatic selection of the necessary algorithms for bringing the text to the final form is carried out to get a real-time response. The designed system uses a certain structure, according to which, at the same time, text analysis is carried out to identify the main idea of a group of proposals, and presents the information received in an ordered form. The system can be upgraded and receive constant support in the form of updates to the relevance databases and calculation of criteria for weight characteristics. It can be implemented in the systems of Internet resources, used as an independent project supporting autonomous operation, or for implementation in intelligent systems. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

PRivATE LEARNING VIA KNOWLEDGE TRANSFER WITH HIGH-DIMENSIONAL TARGETS 47

PRIVATE LEARNING VIA KNOWLEDGE TRANSFER WITH HIGH-DIMENSIONA...

引用

47th IEEE International conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Fay, Dominik Sjolund, Jens Oechtering, Tobias J. KTH Royal Inst Technol Dept Intelligent Syst Stockholm Sweden Uppsala Univ Dept Informat Technol Uppsala Sweden Elekta Instrument Stockholm Sweden

ISBN: (纸本)9781665405409

Preventing unintentional leakage of information about the training set has high relevance for many machine learning tasks, such as medical image segmentation. While differential privacy (DP) offers mathematically rigorous protection, the high output dimensionality of segmentation tasks prevents the direct application of state-of-the-art algorithms such as Private Aggregation of Teacher Ensembles (PATE). In order to alleviate this problem, we propose to learn dimensionality-reducing transformations to map the prediction target into a bounded lower-dimensional space to reduce the required noise level during the aggregation stage. To this end, we assess the suitability of principal component analysis (PCA) and autoencoders. We conclude that autoencoders are an effective means to reduce the noise in the target variables.

关键词： Differential Privacy Machine Learning Knowledge Transfer image Segmentation Compression

来源：评论

学校读者我要写书评

暂无评论

Analysis of Plant Leaf Diseases Recognition using image processing with Machine Learning Techniques

Analysis of Plant Leaf Diseases Recognition using Image Proc...

引用

2022 IEEE International conference on Advances in Computing, Communication and Applied Informatics, ACCAI 2022

作者： Vasudevan, N. Karthick, T. School of Computing SRM Institute of Science and Technology Department of Data Science and Business Systems Chennai India

ISBN: (纸本)9781665495295

Agriculture plays a foremost role in countries growth. The physical recognition of disease in the plant is more timeconsuming and necessity of expert labor is high. One of the most vital aspect in agriculture field is plant disease that reduces quality andquantity of agricultural crops. The machine learning approaches can easily recognize these diseases compared to physical method. So the machine learning techniques in addition toimage processing is used to identify diseased leaf. These methods will help in recognizing plant diseases thus increasing the yield of plants. This paper concentrates on the previous research work that used the characteristics of machine learning techniques in addition to image processing. It describes the various plant disease types, image processing methods and also various techniques of plant disease systems are analyzed with accuracy. Finally, the various challenges in the recognition of plant leaf diseases are identified and listed. © 2022 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

image Based Plant Disease Classification with Cause and Severity Analysis and Remedial Action

Image Based Plant Disease Classification with Cause and Seve...

引用

2023 International conference on Intelligent systems for Communication, IoT and Security, ICISCoIS 2023

作者： Rani, Gopika N Divya Darshini, R. Monirhithikka, S.P. Samsitha Banu, S. Saravu Miththira, V.C. Subashini, B. PSG College of Technology Department of CSE Coimbatore India

ISBN: (纸本)9798350335835

Unlike diseases of the human body, plant diseases don't camouflage themselves within the body of the crop. The leaves reflect the infection with a change in color, shape, texture or a combination of the three. Hence, predictive modelling of the leaf images dataset using machine learning can help detect the disease. Mostly the image processing algorithms is used for predicting the diseases. The Random forest algorithm is used for color segmentation and Convolutional neural networks mainly focuses on disease classification. Vision based plant infection showed efficient results and promising performance. The features are extracted such that they are feasible for a severity analysis. The percentage of severity is extracted from the percentage which is 94.6% of the classification accuracy after which suitable remedial actions are suggested. This offers a comprehensive strategy for addressing the threat of crop diseases that lower agricultural output and waste. (Choice of crop depends on accessibility of dataset). © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

AI-SMLA: An Artificial Intelligence based Smart Machine Learning Algorithm for Complex image Segmentation Issues in Vertex image processing 3

AI-SMLA: An Artificial Intelligence based Smart Machine Lear...

引用

3rd International conference on Electronics and Sustainable Communication systems, ICESC 2022

作者： Reddy, R. Pradeep Kumar Kiran, S. Kumar, A. Ashok Y.S.R Engineering College of Yvu Andhra Pradesh Proddatur India

ISBN: (数字)9781665479714

ISBN: (纸本)9781665479714

Today's machine learning is considered as one of the artificial intelligence technologies used in many ways. Its functions are very accurate, from receiving the given input data to calculating, measuring and outputting it. It is used to calculate a valid result without user intervention. In that order the applications of this machine learning method in digital image processing technology are constantly increasing. This technology is used for everything from overcoming facial identities to calculating the various photo identities of mobile devices currently in use. In this paper a smart machine learning based algorithm has been designed to effectively handle vertex image processing environment and complex image segmentation functions. Its special feature is that it examines the given photos based on its dead pixels and calculates the correct results. There will be no human intervention in this system. The proposed smart algorithm was compared with some existing algorithms. © 2022 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide image Classification 38

FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide...

引用

38th conference on Neural Information processing systems, NeurIPS 2024

作者： Fu, Kexue Luo, Xiaoyuan Qu, Linhao Wang, Shuo Xiong, Ying Maglogiannis, Ilias Gao, Longxiang Wang, Manning Qilu University of Technology Shandong Academy of Sciences Jinan China Digital Medical Research Center School of Basic Medical Sciences Fudan University China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention China Fudan University China University of Piraeus Greece Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

The expensive fine-grained annotation and data scarcity have become the primary obstacles for the widespread adoption of deep learning-based Whole Slide images (WSI) classification algorithms in clinical practice. Unlike few-shot learning methods in natural images that can leverage the labels of each image, existing few-shot WSI classification methods only utilize a small number of fine-grained labels or weakly supervised slide labels for training in order to avoid expensive fine-grained annotation. They lack sufficient mining of available WSIs, severely limiting WSI classification performance. To address the above issues, we propose a novel and efficient dual-tier few-shot learning paradigm for WSI classification, named FAST. FAST consists of a dual-level annotation strategy and a dual-branch classification framework. Firstly, to avoid expensive fine-grained annotation, we collect a very small number of WSIs at the slide level, and annotate an extremely small number of patches. Then, to fully mining the available WSIs, we use all the patches and available patch labels to build a cache branch, which utilizes the labeled patches to learn the labels of unlabeled patches and through knowledge retrieval for patch classification. In addition to the cache branch, we also construct a prior branch that includes learnable prompt vectors, using the text encoder of visual-language models for patch classification. Finally, we integrate the results from both branches to achieve WSI classification. Extensive experiments on binary and multi-class datasets demonstrate that our proposed method significantly surpasses existing few-shot classification methods and approaches the accuracy of fully supervised methods with only 0.22% annotation costs. All codes and models will be publicly available on https://***/fukexue/FAST. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Gas Counter Propagation Neural Network (NG CPNN): A Novel Model for Face Recognition

Neural Gas Counter Propagation Neural Network (NG CPNN): A N...

引用

2024 International conference on Science, Engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Olagunju, Kazeem Michael Samuel Falohun, Adeleye Oke, Alice Oluwafunke Adebiyi, Marion O. Landmark University Directorate of Centre for Systems and Information Services Omu-Aran Nigeria LAUTECH Department of Computer Engineering Ogbomoso Nigeria Landmark University Department of Computer Science Omu-Aran Nigeria

ISBN: (纸本)9798350358155

The advent of biometric technology has enhanced security in various ways, especially by lowering the propensity for circumvention which was obtainable in traditional recognition measures such as the use of passwords, tokens, smart cards, PIN etc. Particularly facial recognition is currently a hot topic, which has evolved over time. A face recognition system is supposed to automatically recognize faces in pictures and videos by receiving a two-dimensional face image as input and comparing it to a predefined database of faces to outputs a discernible face image in the end. Despite the various algorithms used in face recognition, the problems of occlusion, light conditions and facial variation still persist. However, this study has implemented and presented Neural Gas Counter Propagation Neural Network (NG CPNN) as a novel model for face recognition *** implementation of model was carried out using 600 face images, pre-processed by histogram equalization, while face features were extracted by Principal Component Analysis. The novelty of NG CPNN was established by utilizing computational time, sensitivity, and accuracy as performance assessment measures at four distinct threshold values. The result shows computation time of 72.36s, accuracy of 96.25%, sensitivity of 98.33% at 0.8, 0.8, and 0.2 thresholds respectively. Finally, it was concluded based on empirical result and statistical evidence that NG-CPN is a novel model for face recognition. NG CPNN can be employed in access control systems, international borders, smartphone technology, and many more. © 2024 IEEE.

关键词： artificial intelligence biometrics face recognition image processing NG- CPNN pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Employing Tensor Decomposition and Contextual Inference for Reducing the Semantic Discrepancy in image processing 2

Employing Tensor Decomposition and Contextual Inference for ...

引用

2nd IEEE International conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Suneetha, K. Gupta, Namit University Karnataka Bangalore India College of Computing Science and Information Technology Teerthanker Mahaveer University Uttar Pradesh Moradabad India

ISBN: (纸本)9798350369960

Despite the growing need for effective image tagging in both commercial and research domains, the inconsistency between image content and text annotations remains a significant issue. We propose an innovative approach that leverages deep learning and tensor decomposition to enhance the quality of image labelling and eliminate the reliance on labor-intensive manual tagging. Our methodology transforms images into tensors, facilitating the formation of a standardized feature space. We employ a sophisticated five-layer neural network architecture that integrates three-level tensor decomposition to match images with their context groups accurately. This structure is adept at capturing the nuanced patterns in data, which is crucial for reducing the semantic discrepancy between visual and textual information. We have rigorously evaluated our algorithm using the Corel-10K dataset, focusing on the specific case of penguin images, to demonstrate the efficacy of our model. The results showcase a marked improvement in the relevance of generated tags, thereby enhancing the retrieval accuracy and mitigating the issue of inappropriate tag assignment. This work not only contributes to the fields of Machine Learning and Data Mining by refining feature extraction and context estimation techniques but also has significant implications for the development of NLP algorithms that can better interpret and generate descriptive tags for visual content. Moreover, our approach sets the stage for future explorations into the integration of AI-driven image tagging systems with robotic systems for autonomous data handling and organization. © 2023 IEEE.

关键词： Contextual Estimation image Understanding Techniques Semantic Gap Minimization Tensor-Based image Analysis Visual Data Interpretation

来源：评论

学校读者我要写书评

暂无评论

CIFAR-10 Dataset image Classification Using CNN 8th

CIFAR-10 Dataset Image Classification Using CNN

引用

8th International conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Sucharitha, M. Sesha Talpa Sai, P.H.V. Vijayagovindan, Sanjith Razmin, Fabina Ravindran, Byju Kiran Babu, Vadapalli V. S. Naveen Kumar, G.S. Bhaumik, Amiya School of Electronics Engineering VIT-AP University Amaravati India Malla Reddy College of Engineering and Technology Hyderabad India School of Information Technology Lincoln University College Petaling Jaya Malaysia Malla Reddy University Hyderabad India Lincoln University College Petaling Jaya Malaysia

ISBN: (纸本)9789819786657

image classification is an essential technology that is widely used in all aspects of human life. This work combined multiple image feature sources using deep learning algorithms to identify photos from the publicly available CIFAR10 image dataset. The same architecture, which consists of convolution modification and max-pooling of layers connected with several completely linked layers, is used to build most conventional convolutional neural networks (CNNs). This system consists of two steps: Pre-processing and Classification. The modified bilateral filtering method was employed in this study’s preprocessing steps. This study used convolutional neural network (CNN) architectures as suggested by the VGG-19 model to classify the CIFAR10 image dataset. The accuracy, precision, recall, and F1-score of the results are evaluated after simulating the suggested model. The testing results demonstrate that the proposed method reach a recall value of 96.4%, F1-score of 94.1%, accuracy of 97.3%, and maximum precision of 96.1%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Research on Video Content Analysis and Recommendation System Based on image processing Technology in New Media Environment

Research on Video Content Analysis and Recommendation System...

引用

Digital Analysis and processing, Intelligent Computation (DAPIC), International conference on

作者： Bei Zhang Anhui Professional College of Art Hefei Anhui China

ISBN: (数字)9798331536169

ISBN: (纸本)9798331536176

In the new media environment, the research of video content analysis and recommendation system is particularly important. This paper discusses how to use image processing technology to deeply analyze and accurately recommend film and television content. With the diversification of presentation forms and communication channels of film and television content, the problems of information overload and uneven content quality have become increasingly prominent. This study aims to solve these problems and improve the user experience by constructing a video content analysis and recommendation system based on image processing technology. The system includes four core modules: data acquisition, image processing, content analysis and recommendation algorithm. By integrating image processing, machine learning and recommendation algorithm, the whole process from data acquisition to personalized recommendation is implemented efficiently. The experimental results demonstrate that the hybrid recommendation strategy outperforms single algorithms in various evaluation metrics, including accuracy, recall, F1 score, and Mean Reciprocal Rank (MRR), significantly enhancing the precision of recommendations and user satisfaction. This study not only provides a scientific basis and decision support for content creation, distribution, and marketing in the film and television industry but also lays a solid foundation for building more intelligent film and television content recommendation systems.

关键词： Industries Content management TV Machine learning algorithms Accuracy image processing Data acquisition Media User experience Recommender systems

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 << < 67 68 69 70 71 72 73 74 75 76 > >>

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：