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

15,139 篇 会议
247 篇 期刊文献
227 册 图书
3 篇 学位论文

馆藏范围

15,616 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

8,104 篇 工学
- 5,426 篇 计算机科学与技术...
- 2,798 篇 软件工程
- 2,443 篇 电气工程
- 1,573 篇 信息与通信工程
- 1,011 篇 控制科学与工程
- 834 篇 光学工程
- 572 篇 电子科学与技术（可...
- 555 篇 生物医学工程（可授...
- 550 篇 机械工程
- 511 篇 仪器科学与技术
- 419 篇 生物工程
- 286 篇 测绘科学与技术
- 204 篇 航空宇航科学与技...
- 189 篇 交通运输工程
- 180 篇 材料科学与工程（可...
- 145 篇 安全科学与工程
- 119 篇 化学工程与技术
4,114 篇 理学
- 2,771 篇 物理学
- 1,130 篇 数学
- 473 篇 生物学
- 325 篇 系统科学
- 275 篇 统计学（可授理学、...
- 146 篇 化学
1,618 篇 医学
- 1,437 篇 临床医学
- 215 篇 特种医学
- 203 篇 基础医学(可授医学...
- 134 篇 药学(可授医学、理...
859 篇 管理学
- 515 篇 管理科学与工程(可...
- 379 篇 图书情报与档案管...
- 130 篇 工商管理
78 篇 法学
69 篇 农学
42 篇 经济学
40 篇 教育学
28 篇 文学
25 篇 军事学
21 篇 艺术学
1 篇 哲学

主题

2,700 篇 image processing
1,404 篇 image segmentati...
1,148 篇 signal processin...
793 篇 real-time system...
744 篇 cameras
743 篇 feature extracti...
552 篇 image edge detec...
539 篇 signal processin...
479 篇 image reconstruc...
470 篇 image coding
447 篇 algorithm design...
372 篇 deep learning
368 篇 object detection
345 篇 computer vision
344 篇 hardware
337 篇 image color anal...
335 篇 real time system...
333 篇 clustering algor...
333 篇 accuracy
316 篇 computer archite...

机构

22 篇 signal and image...
19 篇 samara national ...
17 篇 school of electr...
12 篇 information syst...
11 篇 samara national ...
11 篇 univ texas san a...
11 篇 department of el...
11 篇 school of electr...
10 篇 department of el...
10 篇 electrical compu...
9 篇 school of electr...
9 篇 institute of ima...
9 篇 tongji universit...
9 篇 purdue univ sch ...
9 篇 university of ch...
9 篇 center for signa...
8 篇 shanghai jiao to...
8 篇 information syst...
8 篇 tampere univ tec...
8 篇 university of to...

作者

22 篇 anon
13 篇 de-shuang huang
12 篇 jagdish chand ba...
11 篇 jie yang
11 篇 p. pirsch
10 篇 hannig frank
10 篇 panetta karen
10 篇 c.-c.j. kuo
10 篇 j.m. mendel
10 篇 plaza antonio
10 篇 r. chellappa
9 篇 semenishchev e.
9 篇 zelensky a.
9 篇 bovik alan c.
9 篇 wei li
8 篇 frank hannig
8 篇 yves wiaux
8 篇 a.s. willsky
8 篇 mahalanobis a
8 篇 ilias maglogiann...

语言

15,262 篇 英文
254 篇 其他
81 篇 中文
26 篇 土耳其文
4 篇 俄文
3 篇 葡萄牙文
2 篇 法文
1 篇 西班牙文

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

共 15616 条记录，以下是481-490 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：

The Impact of Preprocessing on Face Recognition using Pseudorandom Pixel Placement 29

The Impact of Preprocessing on Face Recognition using Pseudo...

引用

29th International conference on systems, Signals and image processing (IWSSIP)

作者： Hadis, Muhammad Sabirin Akita, Junichi Toda, Masashi Nurzaenab Kanazawa Univ Dept Elect Engn & Comp Sci Kanazawa Japan Kumamoto Univ Ctr Management Informat Technol Kumamoto Japan STMIK AKBA Study Program Informat Engn Makassar Indonesia

ISBN: (数字)9781665495783

ISBN: (纸本)9781665495783

The condition of face images, data processing algorithms, and hardware capabilities can influence the accuracy of face recognition. Several studies have been conducted to increase performance of face recognition. One of the steps is to create or even improve the methods in preprocessing as one of the essential steps that can affect accuracy. This paper proposed a pseudorandom pixel placement method applied to the preprocessing step in face recognition to know the impact on accuracy. Eight face objects were used in this study. One face image for one object as training data was taken via a single-lens digital reflex camera and a smartphone. One video for one object was taken from Closed Circuit Television with two different placement angle conditions for testing data. The experiment was carried out with four variations of the basic resolution size of the face image in the testing data to see the performance of the proposed method. The result is five of eight face objects have improved accuracy than without using pseudorandom pixel placement. The best average accuracy result using the proposed method is 63.76% higher than without using the proposed method with a value of 60.09%, so preprocessing using the pseudorandom pixel placement on face recognition can increase accuracy.

关键词： Face Recognition Pseudorandom Pixel Placement One image Training Data image processing Computer vision

来源：评论

学校读者我要写书评

暂无评论

Selection of Color Contrast Objects Against a Non-Stationary Background Using Modified HSV Model 6

Selection of Color Contrast Objects Against a Non-Stationary...

引用

6th IEEE International conference on Information and Telecommunication Technologies and Radio Electronics, UkrMiCo 2023

作者： Popov, Anatoliy Vasilyeva, Irina Kosharskyi, Volodymyr Dergachov, Konstantin National Aerospace University Kharkiv Aviation Institute Department of Aerospace Radioelectronic Systems Kharkiv Ukraine National Aerospace University Kharkiv Aviation Institute Department of Information-Communication Technologies Named after O.O. Zelensky Kharkiv Ukraine National Aerospace University Kharkiv Aviation Institute Department of Aircraft Control Systems Kharkiv Ukraine

ISBN: (纸本)9798350348484

For the development of such smart systems based on the computer vision as, for example, unmanned aerial vehicles, driverless cars, etc. efficient image processing algorithms are required. These algorithms should provide the possibility to process images in a video stream, perform segmentation, select objects and define informative signatures for further recognition. Objects in optical images usually differ in color, shape, may have shadows, and they stand out against the non-stationary background of the terrain;that is why the HSV color model is often used for their selection. To select objects against the background of the terrain it is necessary to define their signatures and train the recognition system. However the variety of objects and the dependence of their color characteristics on changes in illumination pose a considerable problem. The paper proposes an alternative approach - to train the system to recognize the background, and the fragments of the image that are not recognized as the background should be classified as objects. For real-time estimation of the color parameters of the background it is proposed to convert the traditional HSV model into a one-dimensional signature to speed up calculations during processing. processing of the images received from an unmanned aerial vehicle by the proposed method makes it possible to select almost all objects of different colors, shapes and sizes against a heterogeneous background and to define their contours for further recognition. © 2023 IEEE.

关键词： Geometrical optics

来源：评论

学校读者我要写书评

暂无评论

Post-processing of Thresholding or Deep Learning Methods for Enhanced Tissue Segmentation of Whole-Slide Histopathological images

Post-Processing of Thresholding or Deep Learning Methods for...

引用

18th International Joint conference on Biomedical Engineering systems and Technologies, BIOSTEC 2025

作者： Marczyk, Michal Wrobel, Agata Merta, Julia Polanska, Joanna Department of Data Science and Engineering Silesian University of Technology Gliwice44-100 Poland Yale Cancer Center Yale School of Medicine New HavenCT06511 United States Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice44-100 Poland

Digital pathology allows for the efficient storage and advanced computational analysis of stained histopathological slides of various tissues. Tissue segmentation is a crucial first step of digital pathology aimed at eliminating background, pen markings, and other artifacts, reducing image size, and increasing the efficiency of further analysis. In most cases, color thresholding or deep learning models are used, but their effectiveness is reduced due to complex artifacts and huge color variations between slides. We propose a post processing method to increase the tissue segmentation performance of any initial segmentation algorithm. Using a set of 197 manually annotated histopathological images of breast cancer patients and 63 images of endometrial cancer patients, we tested our method with 3 thresholding techniques and 3 deep learning-based algorithms by calculating the Dice index, Jaccard index, precision, and recall. In both datasets, applying post processing increased precision and recall for thresholding methods and mostly precision for deep learning models. Overall, applying post-processing gave better tissue segmentation performance than initial segmentation methods, significantly increasing Dice and Jaccard indices. Our results proved that thanks to post-processing, the tissue segmentation pipeline is more robust to noises and artifacts commonly present in histopathological images. © 2025 by SCITEPRESS– Science and Technology Publications, Lda.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Dual Adversarial Contrastive Learning for Underwater image Enhancement 2

Dual Adversarial Contrastive Learning for Underwater Image E...

引用

2nd International conference on image processing and Media Computing, ICIPMC 2023

作者： Yan, Mengyi Jiang, Xiaoyue Ren, Yuanbo Li, Jiayi Dang, Sihang Feng, Xiaoyi Xia, Zhaoqiang Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350326611

Underwater images are highly distorted, which makes high-level computer vision tasks difficult. Existing underwater image enhancement algorithms mainly focus on restoring the appearance of images. As a result, enhanced images may not be useful for high-level computer vision tasks. The lack of label images also makes most supervised learning networks impractical. In this paper, a dual adversarial contrastive learning enhancement network is proposed, which is both visually friendly and task-oriented. A circular network is proposed to achieve self-supervised learning between unpaired images. We also introduce a contrastive prior between the enhanced and degraded results in feature space to ensure the good visual appearance of the enhanced results. Furthermore, the high-level detection task is also used to constrain the enhanced results. The experiments were carried out on a popular underwater dataset, the enhanced images of the proposed method showed better visual quality and improve tracking performance as well. © 2023 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Advanced HLS for Reconfigurable image processing in Big Data systems 12th

Advanced HLS for Reconfigurable Image Processing in Big Da...

引用

12th International conference on Big Data and Artificial Intelligence, BDA 2024

作者： Bhagirath, K. Pant, Dheeraj Tiwari, Abhishek Khaneja, vivek Noida201309 India

ISBN: (纸本)9783031818202

This paper introduces novel HLS techniques for reconfigurable and memory-efficient image processing within deep learning frameworks, addressing inherent limitations of current deep learning accelerators (DLAs) due to their dependency on the host processor, leading to pipeline delays and reduced throughput. The proposed approach emphasizes parallelization, on-chip buffering, and scalability, enhancing computational efficiency and throughput for AI applications in big data and edge computing environments. Methodologically, the paper emphasizes mathematical analysis, hardware architecture specification, HLS modeling, Verilog RTL implementation. By addressing these challenges, this work contributes to advancing the performance capabilities of DLAs in deep learning inference tasks. The algorithms integrates seamlessly with DLA IP subsystems, such as AXI interfaces, external (DRAM) and internal (SRAM) memory interfaces, and activation/pooling engines. Key contributions include advanced algorithm design to enhance memory efficiency and reconfigurability, essential for adapting to diverse hardware architectures. Experimental validation demonstrates substantial improvements in computational speed and resource utilization compared to traditional methods, making it suitable for intensive AI tasks in big data analytics. In conclusion, this research presents a framework for integrating HLS techniques into hardware accelerators, facilitating efficient image processing across diverse applications in big data and edge computing. These advancements aim to bolster DLAs’ capabilities in handling complex AI workloads effectively, promising enhanced solutions for AI-driven domains. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

RestoreAgent: Autonomous image Restoration Agent via Multimodal Large Language Models 38

RestoreAgent: Autonomous Image Restoration Agent via Multimo...

引用

38th conference on Neural Information processing systems, NeurIPS 2024

作者： Chen, Haoyu Li, Wenbo Gu, Jinjin Ren, Jingjing Chen, Sixiang Ye, Tian Pei, Renjing Zhou, Kaiwen Song, Fenglong Zhu, Lei The Hong Kong University of Science and Technology Guangzhou China Huawei Noah's Ark Lab Canada The University of Sydney Australia The Hong Kong University of Science and Technology Hong Kong

Natural images captured by mobile devices often suffer from multiple types of degradation, such as noise, blur, and low light. Traditional image restoration methods require manual selection of specific tasks, algorithms, and execution sequences, which is time-consuming and may yield suboptimal results. All-in-one models, though capable of handling multiple tasks, typically support only a limited range and often produce overly smooth, low-fidelity outcomes due to their broad data distribution fitting. To address these challenges, we first define a new pipeline for restoring images with multiple degradations, and then introduce RestoreAgent, an intelligent image restoration system leveraging multimodal large language models. RestoreAgent autonomously assesses the type and extent of degradation in input images and performs restoration through (1) determining the appropriate restoration tasks, (2) optimizing the task sequence, (3) selecting the most suitable models, and (4) executing the restoration. Experimental results demonstrate the superior performance of RestoreAgent in handling complex degradation, surpassing human experts. Furthermore, the system's modular design facilitates the fast integration of new tasks and models. © 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

Federated Learning for Enhanced Medical image Analysis 1

引用

12th International conference on Networked systems (NETYS)

作者： Lakrouni, Sanaa Bah, Slimane Sebgui, Marouane Univ Mohammed V Rabat Mohamedia Sch Engineers Smart Commun Res Team Rabat Morocco

ISBN: (数字)9783031673214

ISBN: (纸本)9783031673207;9783031673214

As artificial intelligence (AI) algorithms continue to advance, researchers have leveraged deep neural networks to address a range of challenges in the medical field. These models require a large-scale dataset and high-quality annotated data for model generalization, which is a major challenge in imaging data due to their limited availability in healthcare institutions. Additionally, it is primarily challenging to work with private patient data and share it with an external entity due to the privacy concerns. These challenges of the traditional centralized learning have led to a more efficient decentralized approach. This approach involves training with a diverse range of data from various domains, which are required to enhance model performance. Hence, many researchers have adopted Federated learning as an emerging paradigm to collaboratively train a machine learning model among multiple healthcare institutions without sharing their local private data. However, medical datasets are sourced from different medical institutions;hence they are often acquired by different protocols, scanner types, data modalities, and from different patient populations. Thus, it is inherently heterogeneous which degrades the global model performance in the federated setting. In this paper, we explore the key motivation for using federated learning in the healthcare field and discuss the challenges posed by the diversity and data heterogeneity of medical data from various institutions. Additionally, we present recent works that help mitigate the non-iid data issue in federated learning. Furthermore, we empirically evaluate the federated learning algorithms alongside centralized learning and one site learning using a benchmark medical dataset. Our analysis demonstrates that the adoption of advanced methods in FL enables us to effectively mitigate the data heterogeneity issue while leveraging data privacy and large-scale datasets within the medical domain.

关键词： Federated Learning Healthcare field Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Fingerprint image Enhancement Method Based on U-Net Model 1st

Fingerprint Image Enhancement Method Based on U-Net Model

引用

1st International conference on AI-generated Content, AIGC 2023

作者： Cheng, Yu-Hsin Su, Sheng-Gui Lin, Yih-Lon Hsu, Hsiang-Chen National Yunlin University of Science and Technology Yunlin Taiwan I-Shou University Kaohsiung Taiwan

ISBN: (纸本)9789819975860

Fingerprint image enhancement is a vital image processing technology that finds applications in fingerprint identification, matching, and biometric authentication. Its objective is to improve the performance and accuracy of fingerprint identification systems by enhancing the quality, clarity, and contrast of fingerprint images while reducing noise. Traditional algorithms often require adjusting parameters based on individual fingerprint images, resulting in inconsistent enhancement results. To address this challenge, this paper proposes a deep learning-based approach for fingerprint image enhancement. Experimental results demonstrate the effectiveness of U-Net architecture with different depths and the impact of incorporating attention gate. Actually, a U-Net model with a depth of six achieves superior performance, surpassing other depths, and the inclusion of attention gate further enhances the results. The proposed method not only retains more fingerprint features but also produces smoother structures and reduces noise surrounding the fingerprint image. These findings contribute to advancing fingerprint image enhancement techniques, bolstering the accuracy and performance of fingerprint identification systems in applications such as forensic analysis and biometric authentication. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

COviD-19 and Pneumonia Detection using X-ray image-Based Deep Learning Methods 2

COVID-19 and Pneumonia Detection using X-ray Image-Based Dee...

引用

2nd International conference on Advanced algorithms and Signal image processing, AASIP 2022

作者： Li, Yuxiao McGill University Montreal Canada

ISBN: (纸本)9781510660571

Globally, pneumonia is the leading cause of death for young people and children. An X-ray of the chest is usually used to diagnose pneumonia by a trained specialist. However, the process is tedious and can result in disagreements among radiologists. It is possible to improve diagnostic accuracy through the use of computer-aided diagnostic systems. In this work, the ResNet model was selected to work as the covid-19 and pneumonia detector based on X-ray image. Several experiments are conducted on to achieve an optimal results. © 2022 SPIE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Study on Operational Techniques of Preliminary Refinement of images in Camouflaged Enemy Detection 8th

A Study on Operational Techniques of Preliminary Refinement ...

引用

8th International conference on Information and Communication Technology for Intelligent systems, ICTIS 2024

作者： Suneel, J.S. Dileep, M.R. Department of Master of Computer Applications Visvesvaraya Technological University—Research Centre Nitte Meenakshi Institute of Technology Karnataka Bengaluru India Department of Master of Computer Applications Nitte Meenakshi Institute of Technology Karnataka Bengaluru India

ISBN: (纸本)9789819766833

This study investigates the crucial significance of image processing in the domain of image analysis for the identification and detection of potential threats in advanced defense systems. Real-time images, captured over a wide range of terrains, introduce specific challenges and possibilities for precise target differentiation. The success of subsequent analyses is heavily dependent on the meticulous preprocessing of obtained images, aiming to improve pertinent features and reduce noise interference. It involves a series of operations applied to an image to enhance its quality, correct imperfections, or prepare it for further analysis. Some of the common image preprocessing techniques are Resizing and Rescaling, Normalizing the pixel values, Gray-scale conversion, Cropping, Noise reduction, Contrast enhancement, Edge detection, Thresholding, etc. Also, a wide analysis and survey have been conducted by considering variant parameters that reflect the outcome. By conducting an examination of the literature and carrying out empirical assessments, this study showcases the effectiveness of the proposed preprocessing techniques in enhancing capabilities for detecting adversaries. The outcomes highlight significant enhancements in the precision, robustness, sensitivity, and speed of algorithms designed for enemy detection when employed in conjunction with the specified preprocessing methods. This paper discusses various techniques that influence image analysis and explores the utilization of these techniques across multiple computer vision domains. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： image analysis

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 << < 45 46 47 48 49 50 51 52 53 54 > >>

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：