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

12,591 篇 会议
194 篇 期刊文献
162 册 图书
1 篇 学位论文

馆藏范围

12,948 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

6,553 篇 工学
- 4,300 篇 计算机科学与技术...
- 2,188 篇 软件工程
- 1,910 篇 电气工程
- 1,284 篇 信息与通信工程
- 817 篇 控制科学与工程
- 656 篇 光学工程
- 460 篇 生物医学工程（可授...
- 444 篇 机械工程
- 444 篇 电子科学与技术（可...
- 420 篇 仪器科学与技术
- 316 篇 生物工程
- 240 篇 测绘科学与技术
- 154 篇 材料科学与工程（可...
- 149 篇 航空宇航科学与技...
- 132 篇 交通运输工程
- 102 篇 安全科学与工程
- 86 篇 网络空间安全
3,171 篇 理学
- 2,123 篇 物理学
- 901 篇 数学
- 358 篇 生物学
- 244 篇 系统科学
- 224 篇 统计学（可授理学、...
- 119 篇 化学
1,431 篇 医学
- 1,268 篇 临床医学
- 196 篇 特种医学
- 158 篇 基础医学(可授医学...
- 101 篇 药学(可授医学、理...
694 篇 管理学
- 421 篇 管理科学与工程(可...
- 294 篇 图书情报与档案管...
- 86 篇 工商管理
58 篇 农学
56 篇 法学
29 篇 教育学
27 篇 文学
26 篇 经济学
18 篇 军事学
17 篇 艺术学
1 篇 哲学

主题

2,642 篇 image processing
1,385 篇 image segmentati...
1,141 篇 signal processin...
611 篇 cameras
594 篇 feature extracti...
584 篇 image edge detec...
530 篇 signal processin...
464 篇 image coding
463 篇 image reconstruc...
460 篇 real-time system...
386 篇 algorithm design...
334 篇 image color anal...
308 篇 pixel
306 篇 deep learning
304 篇 image enhancemen...
299 篇 real time system...
292 篇 object detection
289 篇 computer archite...
285 篇 hardware
284 篇 neural networks

机构

22 篇 signal and image...
19 篇 samara national ...
14 篇 school of electr...
11 篇 samara national ...
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...
8 篇 purdue univ sch ...
8 篇 university of ch...
8 篇 electrical compu...
8 篇 image processing...
8 篇 information syst...
8 篇 samara national ...
8 篇 lockheed martin ...
7 篇 school of electr...

作者

19 篇 anon
13 篇 de-shuang huang
12 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
10 篇 a. ortega
9 篇 c.-c.j. kuo
8 篇 frank hannig
8 篇 hannig frank
8 篇 ilias maglogiann...
8 篇 carli m.
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

语言

12,729 篇 英文
131 篇 其他
74 篇 中文
20 篇 土耳其文
3 篇 葡萄牙文
2 篇 德文
2 篇 俄文
1 篇 西班牙文
1 篇 法文

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

共 12948 条记录，以下是361-370 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：

Localization of Dengue Virus Likelihood Using image processing Technique 6

Localization of Dengue Virus Likelihood Using Image Processi...

引用

6th IEEE International conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Hosen, Md. Mahbub Islam, Md. Rahatul Tabassum, Faria Tonni, Syeda Thamina Noor, Malik Mohammad Nafiur Rahman, Shahid Northern University of Bangladesh Dept. of Computer Science and Engineering Dhaka Bangladesh Kyushu Institute of Technology Dept. of Human Intelligence Systems Wakamatsu Kitakyushu Japan Bangladesh University of Engineering and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh Bangladesh Advance Robotics Research Center Human Intelligence Lab Dhaka Bangladesh Canadian University of Bangladesh Dept. of Electrical and Electronic Engineering Dhaka Bangladesh

ISBN: (纸本)9798350306613

The Aedes mosquito, found in tropical areas, transmits, and causes dengue fever. The spread of the dengue fever virus from an infected Aedes mosquito bite typically takes between three and fifteen days to manifest itself clinically as dengue fever symptoms. Early and automated detection of this illness will reduce the occurrence of outbreaks and facilitate the digitization of the system. Our primary objective is to identify regions at high risk for dengue fever using limited image data through the utilization of sophisticated machine learning and image processing methods. This work showcases the application of transfer learning algorithms for the timely identification of regions at risk for dengue mosquito infestation, particularly in situations where obtaining early data on dengue outbreaks is challenging. The experiments included images of 2150 dengue-positive data sets and 1440 dengue-negative data sets. We used AI and image classifiers Yolo V4 Tin, Tensor Flow, Google Colab, etc. for the training data set, and the system makes predictions with a 99.63% accuracy rate. Our system has some unique attributes;it not only detects the percentage of dengue probability but also the specific dengue-prone location on the submitted image. © 2024 IEEE.

关键词： aedes mosquito dengue-prone image processing yolo v4 tiny

来源：评论

学校读者我要写书评

暂无评论

Fractal image Compression Using Discrete Cosine Transform with Domain Classification and Hexagonal Partitioning

Fractal Image Compression Using Discrete Cosine Transform wi...

引用

International conference on Power Engineering and Intelligent systems, PEIS 2024

作者： Kulkarni, Milind Bharadwaj, Rakhi Joshi Hedaoo, Anushka Vishwakarma Institute of Technology Pune India

ISBN: (纸本)9789819767090

image compression has seen much advancement over the years, with new algorithms and techniques being developed to make image files smaller and easier to transmit and store using both lossy compression methods as well as lossless compression techniques. This paper proposes a lossy fractal image compression method using hexagonal partitioning and domain classification on the quantized image pixels to alleviate the image compression technique's processing complexity. Fractal image compression is a technique for compressing digital images that uses the idea of self-similarity, which is the concept that a pattern can repeat itself at different scales. Our proposed method consists of transforming the spatial domain to frequency domain using discrete cosine transform with quantization and then applying hexagonal partitioning on the square image pixels. A range block is compared with every other classified domain block and the domain block having the least root mean squared (RMS) error is mapped to the range block and replaced with it, storing the original contrast and brightness settings. In this manner, an encoding file is created which stores information of all the mappings, and then the original image is decoded iteratively until the output resembles the original image. To evaluate the performance of the suggested algorithm, numerous simulations are performed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Multi-Spectral Stereo-Imaging for Autonomous Farming Using Low-Cost Sensors 10

Multi-Spectral Stereo-Imaging for Autonomous Farming Using L...

引用

10th International conference on Control, Decision and Information Technologies (CoDIT)

作者： Homann, Hanna Boukhris, Fedi Stollmeier, Frank Ufheil, Manuel Will, Jens Christian Hannover Univ Appl Sci & Arts Fac Elect Engn Hannover Germany Fenntec GmbH Hannover Germany

ISBN: (纸本)9798350373981;9798350373974

This paper presents the development of a low-cost, multi-spectral stereo-imaging system designed for autonomous farming applications. With the growing interest in reducing manual labor in organic farming through technological means, especially in tasks such as weeding and plant health monitoring, there is a significant push towards the development of autonomous robotic systems. These systems often rely on advanced imaging techniques for accurate plant identification, health assessment, and navigation. We propose a novel stereo-camera system combining RGB and near-infrared (NIR) imaging to generate Normalized Difference Vegetation Index (NDVI) images for detailed plant health analysis. The system utilizes off-the-shelf components, including a StereoPi board and RaspberryPi 4 compute module, equipped with two IMX219-160 cameras. By removing the NIR blocking filter from one camera, we achieve a dual RGB and NIR imaging capability, enhancing plant-to-soil contrast and improving the detection sensitivity crucial for automated weeding applications. Our approach includes system calibration, stereo-disparity computation, and NDVI image formation, demonstrating the feasibility of stereo-matching between RGB and NIR images through semi-global matching. Preliminary results indicate that the system is capable of producing NDVI images with reasonable quantitative values, offering insights into plant health that could significantly benefit autonomous farming operations. Improved contrast is observed in the NIR band, promising improved robustness of AI-based plant detection algorithms. Further studies will explore the system's potential in automated plant health and growth assessment, as well as its integration into robotic weeding and harvesting systems.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

TPC-NAS: Simple and Effective Neural Architecture Search Based on Total Path Count

TPC-NAS: Simple and Effective Neural Architecture Search Bas...

引用

6th International conference on AI Circuits and systems (AICAS)

作者： Huang, Ming-Shan Chen, Pi-Chuan Chiueh, Tzi-Dar Natl Taiwan Univ Taipei Taiwan

ISBN: (纸本)9798350383638;9798350383645

With the explosive growth of neural network (NN) research and application areas, there is a pressing need to automate the NN model search process in order to attain optimal performance. Nevertheless, existing neural architecture search (NAS) algorithms are time-consuming, resource-intensive, and predominantly tailored for image-related applications. This paper presents the Total Path Count (TPC) score, a straightforward yet highly efficient accuracy predictor solely reliant on the architectural information of a model. The effectiveness of the TPC score is underscored by a robust rank correlation of 0.96 between TPC scores and the accuracies of CIFAR100 architectures. We further introduce TPC-NAS, a zero-shot NAS method that can complete a NAS task in under five CPU minutes without training and inference. TPC-NAS has found wide-ranging applications and it outperforms many other NAS solutions. In image classification, TPC-NAS achieves 78.3% imageNet top-1 accuracy with 399M FLOPs, while in object detection, it improves mAP by at least 2% over other NAS-derived models. Moreover, TPC-NAS successfully discovers a super-resolution architecture with < 300K parameters and achieves 32.09dB PSNR. In NLP, TPC-NAS delivers a model that matches tinyBERT's FLOPs but outperforms it by almost 10% in accuracy. These experiments illustrate TPC-NAS's ability to rapidly generate high-performance CNN/transformer architectures for various applications.

关键词： Neural Architecture Search (NAS) image Classification Super-Resolution Object Detection Natural Language processing

来源：评论

学校读者我要写书评

暂无评论

Turkish Document image Classification

Turkish Document Image Classification

引用

International conference on Advanced Engineering, Technology and Applications, ICAETA 2024

作者： Nar, Meryem Tuğba Durukan, Gürcan Özcan, Abdullah Çakıl, Lütfü Kara, Hüseyin Omurca, Sevinç İlhan GoLive Yazılım Hizmetleri Istanbul Turkey Kocaeli University İzmit Turkey

ISBN: (纸本)9783031709234

Document image classification has gained extensive attention due to the rising number and types of scanned documents. Multi-modal architectures, processing image and text simultaneously, leverage the strengths of each modality. This study explores an efficient neural architecture for classifying scanned documents in a private company. The effectiveness of CNN-based deep learning and OCR algorithms in extracting textual and visual features is investigated. Different feature fusion methods are applied in the next stage to combine these extracted features. A multi-modal document image classifier is developed for companies managing a large number of scanned documents, delivering superior performance even with fewer and faint documents. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play image Reconstruction 38

Provably Robust Score-Based Diffusion Posterior Sampling for...

引用

38th conference on Neural Information processing systems, NeurIPS 2024

作者： Xu, Xingyu Chi, Yuejie Carnegie Mellon University United States

In a great number of applications, the goal is to infer an unknown image from a small number of noisy measurements collected from a known and possibly nonlinear forward model describing certain sensing or imaging modality, which is often ill-posed. Score-based diffusion models, thanks to their impressive empirical success, have emerged as an appealing candidate of an expressive prior in image reconstruction. In order to accommodate diverse tasks at once, it is of great interest to develop efficient, consistent and robust algorithms that incorporate unconditional score functions of an image prior distribution in conjunction with flexible choices of forward models. This work develops an algorithmic framework for employing score-based diffusion models as an expressive data prior in nonlinear inverse problems with general forward models. Motivated by the plug-and-play framework in the imaging community, we introduce a diffusion plug-and-play method (DPnP) that alternatively calls two samplers, a proximal consistency sampler based solely on the likelihood function of the forward model, and a denoising diffusion sampler based solely on the score functions of the image prior. The key insight is that denoising under white Gaussian noise can be solved rigorously via both stochastic (i.e., DDPM-type) and deterministic (i.e., DDIM-type) samplers using the same set of score functions trained for generation. We establish both asymptotic and non-asymptotic performance guarantees of DPnP, and provide numerical experiments to illustrate its promise in various tasks. To the best of our knowledge, DPnP is the first provably-robust posterior sampling method for nonlinear inverse problems using unconditional diffusion priors. © 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

Hardware-aware, deep-learning approaches for image denoising and star detection for star tracker sensor 10

Hardware-aware, deep-learning approaches for image denoising...

引用

10th International conference on Control, Decision and Information Technologies (CoDIT)

作者： Guesmi, Besma Moloney, David Ubot Technol Dublin Ireland

ISBN: (纸本)9798350373981;9798350373974

In recent years, Deep Neural Networks (DNNs) approaches have outperformed traditional techniques for several computer vision problems. This has been made possible by the increase of computational resources represented by Graphical processing Units (GPU) that allow training using large datasets and the availability of deep learning accelerators for inference. On the other hand, the attitude determination accuracy requirements for spacecraft are increasing. The most accurate attitude determination sensor for spacecraft is the so-called star sensor or star tracker. With the increase in lowcost satellite platforms such as CubeSats, research into the improvement of star sensor accuracy for low-power and low-cost sensor architectures remains a relevant subject. In this context, we examine several methods for noise reduction and star detection for improving centroiding performance. More specifically, an efficient and robust denoising method for star images using an Auto-Encoder (AE) is proposed. This method enhances the image quality for systems sensitive to noise. Furthermore, an accurate and lightweight algorithm based on an existing YOLO (You Only Look Once) architecture is proposed to detect the location of stars in the image. In this work, the YOLO bounding boxes are used to describe the space region around the stars. Subsequently, the star centroid within the bounding box is computed using the COG (Center Of Gravity) method. This method removes the need for centroiding algorithms sliding over the entire image area. An extensive comparison of the proposed denoising technique with other traditional filters confirms that the proposed method resists all noise models and reconstructs well the corrupted images. Experiments show that the proposed YOLO-based star detector achieves high accuracy with a lightweight architecture without any extra latency.

关键词： star tracker attitude determination deep learning image preprocessing denoising detection centroiding YOLOv5 autoencoder low-power

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Deep Learning algorithms for image Recognition and Plant Leaf Disease Detection 2

An Enhanced Deep Learning Algorithms for Image Recognition a...

引用

2nd International conference on Augmented Intelligence and Sustainable systems, ICAISS 2023

作者： Asha, V. New Horizon College of Engineering Department of Master of Computer Application Bengaluru India

ISBN: (纸本)9798350325799

Object recognition in photographs has only been possible with the advent of modern deep learning (DL) techniques. Following its success in other fields, DL techniques are increasingly being used to a broad variety of agricultural operations. Due to its intrinsic complexity, image-based plant disease detection is difficult to solve. Targeted management relies on more than just detection and requires accurate identification of each species. An automated disease detection system aids the farmer by providing a speedy and accurate diagnosis of plant illness. Accelerating agricultural diagnostics requires the development of an automated system for identifying plant leaf diseases. Using machine learning and image processing, the authors of this study outline a strategy for detecting leaf blight. A photo of a leaf may be fed into this framework. In a first processing stage, noise is eliminated from the leaf images. The mean filter may be used to get rid of noise. Histogram equalisation is a method for enhancing image quality. Segmentation is a technique used in photography to break a large image down into more manageable sections. This helps to establish the picture's limits. The image is broken up using the BIRCH (Balance Iterative Reducing and Clustering utilising Hierarchies) technique. For this purpose of feature extraction, fine grained classification model, a convolutional neural network is used. After that, the pictures are categorized using a variety of methods, one of which is RCNN (Region based Convolutional neural network). Using this approach, this study discovered the split ratio, computational time, and as a result RCNN has resulted in a high accuracy of 0.98 when detecting the leaf compared to other algorithms. © 2023 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Application-Specific image and Video processing Techniques for Security and Surveillance 15

Application-Specific Image and Video Processing Techniques f...

引用

15th International conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Kalanandhini, G. Sidhu, Amritpal Malathi, H. Dedgaonkar, Suruchi G. Singh, K. Ranjith Rampal, Sourav Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai127 India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh 174103 India Karnataka Bangalore India Department of Information Technology Vishwakarma Institute of Technology Pune India Department of Computer Science Karpagam Academy of Higher Education Coimbatore641021 India Centre of Research Impact and Outcome Chitkara University Punjab Rajpura140417 India

ISBN: (纸本)9798350370249

Utility-particular photo and video processing strategies for protection and surveillance are a set of algorithms and techniques used to procedure and examine pictures and motion pictures captured by protection and surveillance systems. These techniques are used to discover and understand items and identify suspicious activities and music-shifting objects in actual time. Common strategies include motion detection, item recognition, facial recognition, item monitoring, and anomaly detection. Those strategies are used to enhance the accuracy and efficiency of security and surveillance structures and to provide extra dependable and relaxed monitoring. ©2024 IEEE.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Research on deep learning-based channel estimation algorithm in 5G high-speed mobile scenario

Research on deep learning-based channel estimation algorithm...

引用

2024 International conference on Signal processing and Communication Security, ICSPCS 2024

作者： Teng, Wang Jie, Chen Honghe Vocational and Technical College Mengzi Yunnan661199 China

ISBN: (纸本)9781510681699

In the high-speed mobile environment supported by the fifth-generation mobile communication technology, higher vehicle speeds, more frequent switching and wider bandwidth make the design of high-speed mobile communication systems more challenging. High-quality wireless communication technology is needed to support future high-speed mobile scenarios to achieve low-latency and highly reliable communication, among which anti-Doppler frequency shift technology is the key. Based on this, this paper proposes a Rayleigh channel estimation algorithm based on image super-resolution (SR) network. This method models the channel response matrix obtained by the LS method as a two-dimensional image, uses the SR network and image restoration (image restoration, IR) technology for learning optimization, and obtains the channel response at the unknown symbol. The simulation results show that the proposed algorithm is significantly better than the traditional Linear Minimum Mean Square Error (LMMSE) method. Compared with other SR-based channel estimation algorithms under low Signal to Noise Ratio (SNR), it has a 3dB gain and a 5dB gain under high SNR. © 2024 SPIE.

关键词： image reconstruction

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 << < 33 34 35 36 37 38 39 40 41 42 > >>

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：