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

2,380 篇 会议
163 册 图书
77 篇 期刊文献
3 篇 学位论文

馆藏范围

2,623 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,651 篇 工学
- 1,310 篇 计算机科学与技术...
- 527 篇 软件工程
- 437 篇 电气工程
- 314 篇 信息与通信工程
- 169 篇 生物工程
- 152 篇 控制科学与工程
- 149 篇 光学工程
- 134 篇 生物医学工程（可授...
- 80 篇 电子科学与技术（可...
- 56 篇 机械工程
- 56 篇 仪器科学与技术
- 29 篇 网络空间安全
- 26 篇 材料科学与工程（可...
- 25 篇 动力工程及工程热...
- 25 篇 化学工程与技术
- 25 篇 安全科学与工程
700 篇 理学
- 447 篇 物理学
- 185 篇 生物学
- 160 篇 数学
- 38 篇 化学
- 36 篇 统计学（可授理学、...
- 22 篇 系统科学
250 篇 医学
- 218 篇 临床医学
- 76 篇 基础医学(可授医学...
- 45 篇 药学(可授医学、理...
- 27 篇 公共卫生与预防医...
171 篇 管理学
- 103 篇 管理科学与工程(可...
- 75 篇 图书情报与档案管...
- 28 篇 工商管理
27 篇 农学
- 27 篇 作物学
22 篇 法学
15 篇 教育学
6 篇 经济学
6 篇 文学
1 篇 哲学
1 篇 军事学

主题

390 篇 artificial neura...
380 篇 neural networks
273 篇 convolutional ne...
258 篇 image processing
242 篇 artificial intel...
214 篇 deep learning
190 篇 feature extracti...
149 篇 training
112 篇 image segmentati...
104 篇 pattern recognit...
103 篇 accuracy
93 篇 machine learning
90 篇 image classifica...
82 篇 image recognitio...
79 篇 computer vision
75 篇 neurons
72 篇 computational mo...
72 篇 neural network
61 篇 information syst...
57 篇 image processing...

机构

7 篇 częstochowa univ...
6 篇 chongqing univer...
6 篇 king saud univer...
6 篇 hefei university...
6 篇 agh university o...
6 篇 information syst...
6 篇 south china norm...
6 篇 harbin institute...
5 篇 lovely professio...
5 篇 university of ca...
5 篇 democritus unive...
5 篇 department of ma...
4 篇 school of comput...
4 篇 department of ma...
4 篇 univ chinese aca...
4 篇 razak faculty of...
4 篇 department of ma...
4 篇 department of co...
4 篇 tongji universit...
4 篇 the islamic univ...

作者

12 篇 eyas el-qawasmeh
9 篇 de-shuang huang
9 篇 ryszard tadeusie...
9 篇 marcin korytkows...
9 篇 leszek rutkowski
8 篇 jacek m. zurada
8 篇 azizah abd manaf
8 篇 lazaros iliadis
7 篇 rafał scherer
7 篇 lopez-rubio ezeq...
6 篇 haijun zhang
6 篇 tianyong hao
6 篇 jagdish chand ba...
6 篇 zhou wu
6 篇 kedar nath das
6 篇 zhao zhang
6 篇 gelenbe e
6 篇 kusum deep
5 篇 włodzisław duch
5 篇 duoqian miao

语言

2,534 篇 英文
54 篇 其他
22 篇 土耳其文
22 篇 中文
1 篇 西班牙文

检索条件"任意字段=Conference on Applications of Artificial Neural Networks in Image Processing II"

共 2623 条记录，以下是2471-2480 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：

Style Transfer: From Stitching to neural networks

Style Transfer: From Stitching to Neural Networks

引用

Big Data & artificial Intelligence & Software Engineering (ICBASE), International conference on

作者： Xinhe Xu Zhuoer Wang Yihan Zhang Yizhou Liu Zhaoyue Wang Zhihao Xu Muhan Zhao Huaiying Luo University of Illinois Urbana-Champaign Urbana USA Washington University in St. Louis St. Louis USA Georgia Institute of Technology Atlanta USA Carnegie Mellon University Pittsburgh USA Cornell University Ithaca USA

ISBN: (数字)9798331506612

ISBN: (纸本)9798331506629

This article compares two style transfer methods in image processing: the traditional method, which synthesizes new images by stitching together small patches from existing pattern images, and a modern machine learning-based approach that uses a segmentation network to isolate foreground objects and apply style transfer solely to the background. The traditional method excels in creating artistic abstractions but can struggle with seamlessness, whereas the machine learning method preserves the integrity of foreground elements while enhancing the background, offering improved aesthetic quality and computational efficiency. Our study indicates that machine learning-based methods are more suited for real-world applications where detail preservation in foreground elements is essential.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AdaBM: On-the-Fly Adaptive Bit Mapping for image Super-Resolution

AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resol...

引用

conference on Computer Vision and Pattern Recognition (CVPR)

作者： Cheeun Hong Kyoung Mu Lee Dept. of ECE & ASRI IPAI Seoul National University Seoul Korea

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Although image super-resolution (SR) problem has ex-perienced unprecedented restoration accuracy with deep neural networks, it has yet limited versatile applications due to the substantial computational costs. Since differ-ent input images for SR face different restoration difficul-ties, adapting computational costs based on the input image, referred to as adaptive inference, has emerged as a promising solution to compress SR networks. Specifically, adapting the quantization bit-widths has successfully re-duced the inference and memory cost without sacrificing the accuracy. However, despite the benefits of the resul-tant adaptive network, existing works rely on time-intensive quantization-aware training with full access to the origi-nal training pairs to learn the appropriate bit allocation policies, which limits its ubiquitous usage. To this end, we introduce the first on-the-fly adaptive quantization frame-work that accelerates the processing time from hours to sec-onds. We formulate the bit allocation problem with only two bit mapping modules: one to map the input image to the image-wise bit adaptation factor and one to obtain the layer-wise adaptation factors. These bit mappings are cali-brated and fine-tuned using only a small number of calibration images. We achieve competitive performance with the previous adaptive quantization methods, while the processing time is accelerated by × 2000. Codes are available at https://***/Cheeun/AdaBM.

关键词： Training Quantization (signal) Accuracy Adaptive systems Superresolution Bit rate Pipelines

来源：评论

学校读者我要写书评

暂无评论

MFCC coefficient and ANN classifier applied to roadway classification

MFCC coefficient and ANN classifier applied to roadway class...

引用

International conference on Microelectronics, ICM

作者： Mohamed Atibi Mohamed Boussaa Issam Atouf Abdellatif Bennis Mohamed Tabaa LPRI Lab EMSI Casablanca Casablanca Morocco LTI Lab Faculty of Science Ben M'sik Hassan II University of Casablanca Casablanca Morocco

ISBN: (数字)9781728140582

ISBN: (纸本)9781728140599

Currently, Intelligent driver assistance systems provide more satisfactory solutions to the field of road safety. These are based on the use of powerful image or signal processing algorithms in terms of speed, accuracy of calculation and decision making. This document describes an intelligent roadway classification system in real-time in 4 classes: asphalt, gravel, snow and stone road. This system relies on the use and combination of two algorithms; the Mel Frequency Cepstrum Coefficient algorithm that extracts the characteristics of each type of road from the sound due to friction of the vehicle wheels with the road, and Multilayer Perceptron algorithm, which receives its characteristics to its inputs and classifies them. This document also describes the stages of the process of learning and testing. The robustness of this system is shown by the obtained satisfactory experimental results that combine between the respective advantages of the MFCC descriptor and MLP classifier.

关键词： Roads Signal processing algorithms Mel frequency cepstral coefficient artificial neural networks Classification algorithms Neurons Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Discrimination of insulator contamination grades using information fusion of multi-light images

Discrimination of insulator contamination grades using infor...

引用

IEEE International conference on the Properties and applications of Dielectric Materials

作者： Zhiren Tian Lijun Jin Yingyao Zhang Jianyong Ai Chenyi Peng Wei Duan Sch. of Electron. & Inf. Eng. Tongji Univ. Shanghai China

ISBN: (纸本)9781479989041

Flashover occurs more easily on contaminated insulators, which causes great economic losses and has bad effects on power system stability. A new method is introduced to discriminate the contamination grades of high voltage insulators, using information fusion of visible images and infrared images of the insulators. Firstly, three heating models of running insulators-No Dry Band, Dry Band and Dry Band Arc are established and solved by numerical analysis method to find out the differences in temperature rise under different running states. Secondly, we smear 10kV insulators in different contamination grades. Then we take their visible images by camera and infrared images by infrared thermal imager after applying the rated AC voltage for hours in artificial fog chamber in different relative humidity. After image processing, we extract 36 disk color features from the visible images and 7 disk temperature features from the infrared images, and screen out the best features using Fisher discrimination. Then, two BP (Back Propagation) neural networks are trained, one of which takes the selected visible image features as the inputs while another uses the selected infrared image features and relative humidity. Furthermore, we fuse the information of visible images and infrared images on feature level, which raises the accuracy in identifying the sample images. This method may provide effective information for insulator cleaning and flashover prevention.

关键词： BP neural network contamination flashover prewarning information fusion insulators numerical calculation

来源：评论

学校读者我要写书评

暂无评论

Mapping EEG Signals to Visual Stimuli: A Deep Learning Approach to Match vs Mismatch Classification

Mapping EEG Signals to Visual Stimuli: A Deep Learning Appro...

引用

IEEE International conference on Signal processing, Communications and Computing (ICSPCC)

作者： Yiqian Yang Zhengqiao Zhao Qian Wang Yan Yang Jingdong Chen Center of Intelligent Acoustics and Immersive Communications Shaanxi Provincial Key Laboratory of Artificial Intelligence School of Marine Science and Technology Northwestern Polytechnical University Xi'an Shaanxi China Hong Kong University of Science and Technology North Electro-Optic Science & Technology Defense Co. Ltd

ISBN: (数字)9798350366556

ISBN: (纸本)9798350366563

Existing approaches to modeling associations between visual stimuli and brain responses are facing difficulties in handling between-subject variance and model generalization. Inspired by the recent progress in modeling speech-brain response, we propose a “match-vs-mismatch” deep learning model in this study to classify whether a video clip elicits neural responses in recorded EEG signals. Our model employs dilated convolutional neural networks and gated recurrent units to extract features from both EEG and video signals, enabling the learning of associations between visual content and corresponding neural recordings. We demonstrate that our proposed model achieves the highest accuracy on unseen subjects compared to other baseline models. Additionally, we assess inter-subject noise using a subject-level silhouette score in the embedding space, revealing that our model effectively mitigates inter-subject noise and significantly reduces the silhouette score. Furthermore, we investigate Grad-CAM activation scores, revealing that brain regions linked to language processing contribute most to model predictions, followed by regions associated with visual processing. These findings hold promise for advancing neural recording-based video reconstruction and related applications.

关键词： Deep learning Visualization Accuracy Noise Predictive models Brain modeling Feature extraction Electroencephalography Vectors image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Multi-Crop Leaf Disease Detection using Deep Learning Methods

Multi-Crop Leaf Disease Detection using Deep Learning Method...

引用

IEEE India conference (INDICON)

作者： Shristy Kashyap Tavisha Thaware Shubham Raj Sahu Mallikharjuna Rao K Electronics and Communication Engineering Internationa Institute of Information Technology Naya Raipur Chhattisgarh India Data Science and Artificial Intelligence Internationa Institute of Information Technology Naya Raipur Chhattisgarh India

ISBN: (纸本)9781665452724

The image processing technique is a method useful in agricultural processes for enhancing accuracy and uniformity of processes in farming while decreasing farmers’ manual observation. Leaf disease detection using deep learning applications can be helpful for farmers to analyze the affected leaves at an early stage which will in turn aid in the agricultural process. In this paper, we have used Convolution neural Network (CNN), a deep learning algorithm mainly used for analyzing visual imagery, for the detection of various crop leaf diseases. The CNN-based model will help in differentiating between diseased and healthy leaves, which will improve farmers’ harvest quality. The main objective of the paper is to create a new dataset that contains three plant leaves that are cauliflower, tomato, and mango, and then compare the accuracy using various CNN models which are generally used for unstructured datasets i.e., images. Also analyzing the results on the basis of different experimental configurations such as choice of deep learning architecture, choice of dataset type, and Choice of training-testing set distribution. Results achieved from these experiments display the performance and precision of the model best fit for disease detection of plants.

关键词： Deep learning Visualization Convolution image processing neural networks Crops Manuals

来源：评论

学校读者我要写书评

暂无评论

Dual Forward-Backward Unfolded Network for Flexible Plug-and-Play

Dual Forward-Backward Unfolded Network for Flexible Plug-and...

引用

European Signal processing conference (EUSIPCO)

作者： Audrey Repetti Matthieu Terris Yves Wiaux Jean-Christophe Pesquet Department of Actuarial Mathematics & Statistics Heriot-Watt University Edinburgh UK Signals and Systems Institute of Sensors Heriot-Watt University Edinburgh UK Université Paris-Saclay CentralcSupélec Inria Center for Visual Computing Gif sur Yvette France

ISBN: (数字)9789082797091

ISBN: (纸本)9781665467995

Proximal methods have been extensively used to find maximum a posteriori (MAP) estimates of unknown images from degraded measurement. Recently, they have been mixed with neural networks (NN) to further improve the reconstruction quality. Two approaches can be distinguished: unfolded NNs, implementing a given iteration number of an optimisation algorithm, and plug-and-play (PnP) algorithms, incorporating NNs in existing optimisation algorithms. Unfolded NNs usually incorporate the measurement operator in the learning process, which can be prohibitive for applications with non-fixed measurement operators. PnP do not have this drawback, but involved NNs still depend on the underlying statistical models (e.g., higher noise level on the measurements requires stronger denoisers). In this work, we propose a PnP algorithm based on forward-backward (FB) iterations, where the learned denoiser is an unfolded NN based on dual-FB iterations. This NN is built to mimic a Gaussian denoiser from a MAP viewpoint. This allows us to introduce a regularisation parameter in the model to tune the regularization strength, similarly to standard variational approaches. This has the advantage of making the learned NN more adaptive to a variety of inverse problem statistical models, without requiring to train the NN for different noise levels.

关键词： Adaptation models Inverse problems Signal processing algorithms artificial neural networks Signal processing image restoration Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Select and Sample - A Model of Efficient neural Inference and Learning 11

Select and Sample - A Model of Efficient Neural Inference an...

引用

Annual conference on neural Information processing Systems

作者： Jacquelyn A. Shelton Joerg Bornschein Abdul-Saboor Sheikh Pietro Berkes Joerg Luecke Frankfurt Institute for Advanced Studies Goethe-University Frankfurt Germany Volen Center for Complex Systems Brandeis University Boston USA

ISBN: (纸本)9781618395993

An increasing number of experimental studies indicate that perception encodes a posterior probability distribution over possible causes of sensory stimuli, which is used to act close to optimally in the environment. One outstanding difficulty with this hypothesis is that the exact posterior will in general be too complex to be represented directly, and thus neurons will have to represent an approximation of this distribution. Two influential proposals of efficient posterior representation by neural populations are: 1) neural activity represents samples of the underlying distribution, or 2) they represent a parametric representation of a variational approximation of the posterior. We show that these approaches can be combined for an inference scheme that retains the advantages of both: it is able to represent multiple modes and arbitrary correlations, a feature of sampling methods, and it reduces the represented space to regions of high probability mass, a strength of variational approximations. neurally, the combined method can be interpreted as a feed-forward preselection of the relevant state space, followed by a neural dynamics implementation of Markov Chain Monte Carlo (MCMC) to approximate the posterior over the relevant states. We demonstrate the effectiveness and efficiency of this approach on a sparse coding model. In numerical experiments on artificial data and image patches, we compare the performance of the algorithms to that of exact EM, variational state space selection alone, MCMC alone, and the combined select and sample approach. The select and sample approach integrates the advantages of the sampling and variational approximations, and forms a robust, neurally plausible, and very efficient model of processing and learning in cortical networks. For sparse coding we show applications easily exceeding a thousand observed and a thousand hidden dimensions.

关键词： Learning Sparse coding state space parametric representation sensory stimulation Combined Method sampling methods Probability distribution approximation Markov chain monte carlo methods

来源：评论

学校读者我要写书评

暂无评论

A novel parallel neural network classifier for automatic vehicle license plate recognition

A novel parallel neural network classifier for automatic veh...

引用

2014 International conference on artificial Intelligence and Industrial Application (AiiA2014)

作者： X.Han H.M.Xie G.Q.Zhang Northwestern Polytechnical University SiChuan University

ISBN: (纸本)9781784660529

In current intelligent transport systems, a license plate recognition subsystem is a critical and important tool for efficiently implementing automatic license plate recognition tasks. The system needs subsystems for image pre-processing, license plate locating, license plate character segmentation, classification and result display sections, where the classification and recognition is the core. This paper illustrates implementations of all the steps and focuses on a multilayer feed-forward neural network classifier. neural network has good nonlinear function approximation capability and classification computing ability. The SIFT(Scale Invariant Feature Transform) feature is introduced into the template matching classifier subsystem because it has good characteristics such as scale, rotation and illumination invariant. Using a large number of real-measured data to do experiments, we parallelized the novel neural network classifier and compared it to the SIFT template matcher classifier. The results show that the proposed method is effective, with a recognition accuracy rate of over 80%.

关键词： vehicle license plate recognition(VLPR) license plate locating character segmentation scale invariant feature transform(SIFT) feature extraction neural networks(NN)

来源：评论

学校读者我要写书评

暂无评论

4.7 A 91mW 90fps Super-Resolution Processor for Full HD images

4.7 A 91mW 90fps Super-Resolution Processor for Full HD Imag...

引用

IEEE International conference on Solid-State Circuits (ISSCC)

作者： Hsueh-Yen Shen Yu-Chi Lee Tzu-Wei Tong Chia-Hsiang Yang National Taiwan University Taipei Taiwan

ISBN: (数字)9781728195490

ISBN: (纸本)9781728195506

Super resolution is the process of reconstructing a high-resolution (HR) image from a low-resolution (LR) one. Super-resolution technology enables high-resolution video streaming, image zoom-in, and far object recognition. Fig. 4.7.1 shows such an application scenario. The details of the videos/images can be reconstructed and projected to a higher-resolution screen, thereby providing a better visual experience. A hardware accelerator is needed to speed up the super-resolution process to support real-time high-resolution video streaming. Conventionally, dictionary-based approaches, such as ANR/GR and A+, convert the LR image into the HR one from learned mapping functions. neural network (NN)-based algorithms generate better-quality super-resolution images by extracting features from training. However, the complexity of the dictionary-based and the NN-based algorithms is excessively high, making them unsuitable for high-speed applications. A rapid and accurate image super resolution (RAISR) algorithm is proposed to achieve comparable quality with a much faster processing speed when compared to the previous solutions. It employs pre-learned filters to enhance the image quality based on bicubic interpolation. A pre-learned filter (also known as kernel) is selected by a hash function to address the structure-related details.

关键词： Visualization Superresolution artificial neural networks Streaming media Filtering algorithms Feature extraction 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263页 << < 244 245 246 247 248 249 250 251 252 253 > >>

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：