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

5,905 篇 会议
124 册 图书
82 篇 期刊文献

馆藏范围

6,111 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,643 篇 工学
- 3,001 篇 计算机科学与技术...
- 1,517 篇 软件工程
- 950 篇 信息与通信工程
- 844 篇 电气工程
- 713 篇 生物工程
- 393 篇 生物医学工程（可授...
- 387 篇 光学工程
- 375 篇 控制科学与工程
- 144 篇 电子科学与技术（可...
- 138 篇 机械工程
- 111 篇 网络空间安全
- 104 篇 仪器科学与技术
- 100 篇 安全科学与工程
- 86 篇 化学工程与技术
- 75 篇 动力工程及工程热...
- 69 篇 交通运输工程
1,470 篇 理学
- 754 篇 生物学
- 648 篇 物理学
- 358 篇 数学
- 126 篇 统计学（可授理学、...
- 99 篇 化学
747 篇 医学
- 659 篇 临床医学
- 184 篇 基础医学(可授医学...
- 122 篇 药学(可授医学、理...
- 82 篇 特种医学
- 65 篇 公共卫生与预防医...
514 篇 管理学
- 276 篇 管理科学与工程(可...
- 274 篇 图书情报与档案管...
- 75 篇 工商管理
88 篇 农学
- 85 篇 作物学
49 篇 法学
34 篇 教育学
18 篇 经济学
9 篇 军事学
8 篇 文学
2 篇 艺术学
1 篇 哲学

主题

1,165 篇 convolutional ne...
1,137 篇 deep learning
904 篇 neural networks
658 篇 machine learning
622 篇 training
495 篇 feature extracti...
346 篇 accuracy
275 篇 computational mo...
249 篇 image classifica...
246 篇 image processing
245 篇 image segmentati...
226 篇 computer vision
220 篇 image recognitio...
191 篇 deep neural netw...
181 篇 visualization
171 篇 artificial intel...
170 篇 transfer learnin...
159 篇 computer archite...
158 篇 convolution
148 篇 artificial neura...

机构

22 篇 chitkara univers...
9 篇 karnataka bangal...
9 篇 information syst...
9 篇 university of el...
8 篇 school of comput...
8 篇 carnegie mellon ...
8 篇 school of comput...
8 篇 harbin institute...
7 篇 shanghai jiao to...
7 篇 hefei university...
7 篇 south china norm...
7 篇 tongji universit...
7 篇 tech univ munich...
6 篇 chongqing univer...
6 篇 maharishi school...
6 篇 school of comput...
6 篇 univ chinese aca...
6 篇 king saud univer...
6 篇 department of co...
6 篇 swiss fed inst t...

作者

14 篇 eyas el-qawasmeh
13 篇 de-shuang huang
8 篇 azizah abd manaf
7 篇 andrea vedaldi
7 篇 horst bischof
7 篇 mohana
7 篇 lazaros iliadis
7 篇 roy kaushik
6 篇 haijun zhang
6 篇 tianyong hao
6 篇 jan-michael frah...
6 篇 thomas brox
6 篇 zhou wu
6 篇 gokhan bilgin
6 篇 rueckert daniel
6 篇 liu chang
6 篇 zhao zhang
6 篇 chrisina jayne
6 篇 hu clj
5 篇 li li

语言

5,873 篇 英文
182 篇 其他
47 篇 中文
34 篇 土耳其文
1 篇 俄文

检索条件"任意字段=Conference on Applications of Neural Networks and Machine Learning in Image Processing IX"

共 6111 条记录，以下是211-220 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：

Integrating machine learning & Deep learning for image Captioning and Text Recognition in Mobile Apps Development

Integrating Machine Learning & Deep Learning for Image Capti...

引用

International conference on Electrical, Computer and Communication Engineering (ECCE)

作者： J. Rahman S. R. Bhowmik Akib Jayed Islam Sultanus Salehin Muhammad Jawad Chowdhury Computer Science & Engineering Port City International University Chattogram Bangladesh Department of Computer Science Norwegian University of Science & Technology Gjøvik Norway Electrical & Computer Engineering The University of Alabama Tuscaloosa USA Computer Science & Engineering Islamic University of Technology Gazipur Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Deep learning methods are increasingly being applied to mobile applications for word recognition and image captioning, offering innovative solutions to complex tasks. In this study, models such as VGG19, ResNet101, and InceptionV3 Hybrid models, functioning as encoders in conjunction with LSTM decoders, are leveraged to generate natural language descriptions of images using the Flickr8k dataset. Furthermore, various machine learning techniques—such as Support Vector machines (SVM), Random Forest, K-Nearest Neighbors (KNN), Logistic Regression, Naive Bayes, and Decision Trees—are evaluated for Bangla text categorization. Deep learning models, including CNNs, hybrid models, and VGG19, are applied for classifying English text and non-text images. A unique hybrid model combining CNN, VGG19, and LSTM is introduced to differentiate between text and non-text images in the English dataset. For nontext images, vision-based frameworks are employed to generate image captions. Moreover, two mobile applications developed using Android Studio are presented: the first enables live text scanning with text-to-speech conversion, while the second supports OCR-based text recognition from gallery images, providing voice outputs in both Bangla and English. Additionally, the research extends to handwritten word recognition through CNNs, RNNs, and Connectionist Temporal Classification (CTC) models, alongside CAPTCHA image recognition utilizing a combination of CNNs, OCR, and CTC techniques.

关键词： Deep learning Support vector machines image recognition Text recognition Optical character recognition Text categorization Nearest neighbor methods Mobile applications Convolutional neural networks Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Reviving Poor Object Segmentations in OOD Medical images using Variational-Deep-PCA Modeling on Segmentation Maps with Sampling-Free learning

Reviving Poor Object Segmentations in OOD Medical Images usi...

引用

IEEE Workshop on applications of Computer Vision (WACV)

作者： Jimut B. Pal Shantanu Welling Himali Saini Suyash P. Awate Centre for Machine Intelligence and Data Science Indian Institute of Technology (IIT) Bombay Computer Science and Engineering Department Indian Institute of Technology (IIT) Bombay

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

For object segmentation in medical images, deep neural networks (DNNs) typically perform poorly on out-of-distribution (OOD) images stemming from the large variability in image-acquisition equipment and protocols across sites. However, we observe that the variability in the underlying object-segmentation maps is far lower. Thus, we propose a novel DNN framework to model this variability in segmentation maps, and leverage it to revive poor segmentations produced by existing DNNs on OOD images. Our DNN framework (i) learns the principal modes of variation in a class of segmentation maps, (ii) models each segmentation map using a low-dimensional mixture-of-modes latent representation on a simplex, (iii) enables sampling-free variational learning and uncertainty estimation, and (iv) trains using small in-distribution image sets. In special cases when OOD-image segmentations are extremely poor, we propose a human-in-the-loop method needing minuscule human intervention. Results using 6 publicly-available datasets and 8 existing DNN segmenters show the benefits of our framework in OOD-image object segmentation.

关键词： Geometry image segmentation Uncertainty Protocols Computational modeling Estimation Object segmentation Artificial neural networks Human in the loop Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Paddycrops Disease Prediction Using image processing by Using 3DCNN

Paddycrops Disease Prediction Using Image Processing by Usin...

引用

International conference on Inventive Computation Technologies (ICICT)

作者： Chandru R S. Lakshmanan Department of Computer Applications Hindustan Institute of Technology and Science Chennai Tamil Nadu

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Paddy plant diseases seriously displace agricultural production, thereby causing heavy economic losses. An effective response to any disease management would depend upon the timely and accurate diagnosis of some of the common diseases, such as leaf smut, bacterial leaf blight, and brown spot. However, conventional means of manual detection are generally laborious, time-consuming, and may invite errors. The proposal for an automated paddy disease detection system with deep learning and high-resolution image analysis aims to address these very challenges. Since the feature extraction and classification of infected paddy leaves are carried out through a 3D Convolutional neural Network (3DCNN), image preprocessing techniques were utilized to enhance image visibility before modeling and training. Its performance of over 99.80% accuracy has surpassed that of conventional methods by a margin. This research offers a precision agriculture tool that provides disease detection with enhanced reliability, scalability, and efficiency. The findings validate the role of deep-learning technologies in diagnostic capabilities for agriculture and are increasingly helping early recognition of diseases to assist with subsequent management decisions.

关键词： Deep learning Training Solid modeling Accuracy Three-dimensional displays Scalability Convolutional neural networks Reliability Proposals Diseases

来源：评论

学校读者我要写书评

暂无评论

HOPE: A Memory-Based and Composition-Aware Framework for Zero-Shot learning with Hopfield Network and Soft Mixture of Experts

HOPE: A Memory-Based and Composition-Aware Framework for Zer...

引用

IEEE Workshop on applications of Computer Vision (WACV)

作者： Do Huu Dat Po-Yuan Mao Tien Hoang Nguyen Wray Buntine Mohammed Bennamoun VinUniversity Academia Sinica VNU-UET University of Western Australia

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Compositional Zero-Shot learning (CZSL) has emerged as an essential paradigm in machine learning, aiming to overcome the constraints of traditional zero-shot learning by incorporating compositional thinking into its method-ology. Conventional zero-shot learning has difficulty managing unfamiliar combinations of seen and unseen classes because it depends on pre-defined class embeddings. In contrast, Compositional Zero-Shot learning leverages the inherent hierarchies and structural connections among classes, creating new class representations by combining at-tributes, components, or other semantic elements. In our paper, we propose a novel framework that for the first time combines the Modern Hopfield Network with a Mixture of Experts (HOPE) to classify the compositions of previously unseen objects. Specifically, the Modern Hopfield Network creates a memory that stores label prototypes and identifies relevant labels for a given input image. Subsequently, the Mixture of Expert models integrates the image with the appropriate prototype to produce the final composition classi-fication. Our approach achieves SOTA performance on sev-eral benchmarks, including MIT-States and UT-Zappos. We also examine how each component contributes to improved generalization.

关键词： Computer vision Zero shot learning Semantics MIMICs Hopfield neural networks Prototypes machine learning Benchmark testing Standards

来源：评论

学校读者我要写书评

暂无评论

Enhancing Accuracy of Handwritten Character Segmentation Using Region-Based Convolutional neural networks (R-CNN)

Enhancing Accuracy of Handwritten Character Segmentation Usi...

引用

AIML-applications for Engineering & Technology (ICAET), International conference on

作者： Kanchan Varpe Sachin Sakhare Rahul Joshi Department of Computer Engineering Vishwakarma Institute of Information Technology Pune India Department of Computer Science and Engineering Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798350355611

ISBN: (纸本)9798350355628

Handwritten character segmentation plays a pivotal role in the performance of Optical Character Recognition (OCR) systems. This paper introduces an innovative approach to enhancing segmentation accuracy using Region-Based Convolutional neural networks (R-CNN). Traditional methods often struggle with issues such as varying character sizes, overlapping, and inconsistent writing styles, leading to suboptimal recognition results. The proposed R-CNN model addresses these challenges by effectively localizing and segmenting individual characters from handwritten text images. The methodology involves training the R-CNN on a comprehensive dataset of handwritten characters, annotated to capture diverse styles and complexities. The model leverages deep learning's feature extraction capabilities and region-based localization to accurately segment characters, even in challenging scenarios like connected or touching characters. Comparative experiments show that the proposed approach outperforms conventional techniques in terms of segmentation accuracy and robustness. Results demonstrate significant improvements, with the R-CNN model achieving higher precision and recall rates across multiple handwritten datasets, including different languages and scripts. This advancement holds promise for enhancing OCR systems used in applications such as automated document processing and digital archiving. Future work will focus on integrating this segmentation method with advanced recognition models to further boost overall handwritten text recognition performance.

关键词： Training Performance evaluation Deep learning image segmentation Accuracy Quantization (signal) Text recognition Optical character recognition Writing Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Ensemble learning-based image Captioning with NLP for Context-Aware Descriptions

Ensemble Learning-based Image Captioning with NLP for Contex...

引用

International conference on ent Computing and Control Systems (ICICCS)

作者： P. M. Naidu S. Dhanesh Sai M. Naveen Ch. Anil Kumar Department of Computer Science and Engineering (AI & ML) Vignan Institute of Technology and Science Nalgonda Telangana India

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

image captioning is a challenging task that requires an appropriate combination of computer vision and natural language processing to describe an image accurately and with context relevance. This paper presents an advanced method for captioning images using an ensemble learning setup along with an NLP-based fusion layer. The proposed system analyzes images from various perspectives by using multiple pre-trained models to capture diverse features, and the generated captions are then combined into a single coherent description using the fusion layer. The system’s efficiency is demonstrated using popular evaluation metrics such as BLEU, ROUGE, and METEOR, showing high accuracy and computational efficiency. This system is designed to work efficiently for a variety of image types, ensuring scalability and real-time application compatibility. The proposed method addresses common challenges in image captioning, including ambiguity, context preservation, and ensuring relevance across different datasets. Qualitative evaluation confirms the system’s ability to produce human-like captions, making it suitable for a wide range of applications such as assistive technologies, autonomous systems, and content generation.

关键词： Measurement Deep learning Scalability Feature extraction Control systems Natural language processing Real-time systems Meteors Ensemble learning Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cross-Domain Data Analytics Through Multi-source Transfer learning 3rd

Enhancing Cross-Domain Data Analytics Through Multi-source T...

引用

3rd International conference on Cyberspace Simulation and Evaluation, CSE 2024

作者： Li, Jiarong Wang, Jingge Wang, Jingyang Xu, Chihan Wang, Hao Zhang, Chaobo Liang, Xiaojun Ding, Wenbo Gui, Weihua Pengcheng Laboratory Shenzhen 518055 China Tsinghua-Berkeley Shenzhen Institute Shenzhen International Graduate School Tsinghua University Shenzhen 518055 China RISC-V International Open Source Laboratory Shenzhen 518055 China Advanced Technology Research Institute Beijing Institute of Technology Beijing 100081 China School of Future Technology South China University of Technology Guangzhou 511442 China School of Automation Central South University Changsha 410083 China

ISBN: (纸本)9789819645053

The rapid evolution of machine learning and computer vision has given rise to numerous new tasks, primarily driven by deep convolutional neural networks’ ability to create complex mappings between feature space X and label space Y. These tasks often necessitate large-scale, human-labeled datasets for supervised training of the network. However, manual labeling is both costly and time-consuming. To overcome this hurdle, it is imperative to develop algorithms that can leverage existing labeled datasets to extract knowledge about the target domain. While most prior research has focused on single-source transfer learning, our study delves into multi-source transfer across various domains and tasks. The paper presents an improved cross-domain data analytics model that supports multi-source transfer learning by training a classifier to re-weight different sources and adjusting the rich and intricate information among sources to boost target learning. Experiments involving two source domains transferring to a single target domain showcase the effectiveness of our methodology. The model’s potential applications in image recognition include object recognition, medical imaging diagnosis, and so on. Future research could explore the scalability of the model to accommodate larger datasets and further refine the transfer learning process for more efficient knowledge extraction. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural Network Deep learning image Classification Multi-source Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Robustness of Fruit and Vegetable image Classification Against Adversarial Attacks Through Defensive Strategies

Enhancing Robustness of Fruit and Vegetable Image Classifica...

引用

IT Innovation and Knowledge Discovery (ITIKD), International conference on

作者： Dhuha Khalid Alferidah Abdulelah Abdullah Algosaibi Alaa Sagheer Ahmed Afifi Abdullah Algosaibi Department of Computer Science College of Computer Science and Information Technology (CCSIT) King Faisal University (KFU) Alahssa Saudi Arabia Department of Environment and Natural Resources College of Agricultural and Food Sciences Faisal University (KFU) Alahssa Saudi Arabia

ISBN: (数字)9798350355468

ISBN: (纸本)9798350355475

Typically, machine learning models allow number of applications including recognition and classification. The adversarial machine learning attack fools the machine learning and deep learning models by initiating a noise attack over the models. The adversarial attack targets the machine learning models to harm the models in a way that the models start classifying the images incorrectly. This leads to increasing the error rate and decreasing the accuracy rate of the machine learning models. The attack is not visible to the human eye to detect. Only the machine learning models can detect the changes. Before and after the attack, all images look identical for the human eye. In this study, we introduce a deep learning model that classifies fruit and vegetable images. Then, we conduct an experiment on the deep learning model. The experiment has two folds, in the first fold we apply three different adversarial attack methods on the model which are the Fast Gradient Sign Method (FGSM), Iterative Fast Gradient Sign Method (I-FGSM) and Momentum Iterative Fast Gradient Sign Method (MI-FGSM). We measure the model's performance in term of accuracy scores before and after applying each attack. The model's performance degrades, and the accuracy scores drops down because of the adversarial attack methods. The scientific experiment we conduct shows the decrease in the accuracy scores over different values of epsilon. The second fold of the study is implementing three different defense strategies into the model which are the distilled neural network, adversarial training, and binary thresholding. We measure the model's performance after applying the defense strategies individually. The model becomes more robust against the adversarial attack, and the accuracy scores of the model increases because of the defense lines incorporated into the model. The experimental results show that only the distilled neural network and the adversarial training strategies successfully protected the mode

关键词： Deep learning Training Technological innovation Accuracy neural networks Noise Knowledge discovery Adversarial machine learning Robustness Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Profiling Mushrooms in the Philippines Using Ensemble Transfer learning

Profiling Mushrooms in the Philippines Using Ensemble Transf...

引用

Computer applications (ICCA), IEEE conference on

作者： Miguel Andrei P. Algarme Sealtiel Rae P. Villegas Department of Computer Information Sciences and Mathematics University of San Carlos Cebu City Philippines

ISBN: (数字)9798331534592

ISBN: (纸本)9798331534608

Profiling mushrooms in the Philippines is crucial for their conservation, contributions to different fields of study, and raising health awareness regarding edible and non-edible species. The identification of mushrooms faces several challenges, including environmental climate conditions, the introduction of non-native species, and the variability in mushroom appearances across the country. To address these challenges, this study introduces an ensemble transfer learning model utilizing ResNet50, InceptionV3, and EfficientNet-B5 models. These models, pre-trained on imageNet, have shown significant accuracy in image classification while maintaining a balance of efficiency and cost. The models are trained using 8,000 samples from the Mushroom Observer dataset as well as images of mushrooms collected from the Philippines. A stacked ensemble technique is employed, and XGBoost is used as the meta-model to combine the base models' predictions. The testing results achieved an accuracy of 94.25%, with precision at 92.08%, recall at 96.83%, and an F1-score of 94.39%. These results show the strength of the ensemble model in identifying the edibility of various mushroom species. This study contributes to advancements in image classification models and machine learning techniques, with a focus on promoting informed mushroom consumption and enhancing awareness across fields of study.

关键词： Accuracy Computational modeling Transfer learning Predictive models Observers Ensemble learning Tuning image classification Residual neural networks Testing

来源：评论

学校读者我要写书评

暂无评论

Efficient Object Detection on Low-Resource Devices Using Lightweight MobileNet-SSD

Efficient Object Detection on Low-Resource Devices Using Lig...

引用

Intelligent Systems and Computational networks (ICISCN), International conference on

作者： Suganya Devi K Sekar K Dheepa T Sheethal R Suvarna Smita R S Teja V Dixit Department of CSE National Institute of Technology Silchar Silchar India Department of AIML Rajalakshmi Engineering College Chennai India Department of CSE Kongunadu College of Engg. and Tech. Tiruchirappalli India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

In the modern era, lightweight and deep learning-driven detection methods are essential for devices with limited computational resources. Object detection is a critical task that powers diverse applications, ranging from autonomous vehicles and security surveillance to augmented reality systems. These applications typically operate on devices constrained by minimal processing power and memory capacity. This study proposes an efficient object detection framework tailored for resource-constrained devices, leveraging a lightweight neural network architecture. The framework integrates the MobileNet Single Shot Detector (SSD) module, utilizing depthwise separable convolutions to significantly reduce computational load while maintaining high accuracy. The proposed lightweight MobileNet-SSD achieved accuracy, precision, recall, and confidence scores of 98.25%, 100%, 95%, and 96%, respectively. Experimental evaluations demonstrate that the proposed method strikes an optimal balance between performance and efficiency, making it suitable for real-time deployment in resource-constrained environments.

关键词： Performance evaluation Training Accuracy Surveillance image processing neural networks Object detection Real-time systems Security Intelligent 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 << < 18 19 20 21 22 23 24 25 26 27 > >>

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：