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

1,442 篇 会议
43 册 图书
43 篇 期刊文献

馆藏范围

1,528 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,211 篇 工学
- 1,041 篇 计算机科学与技术...
- 602 篇 软件工程
- 285 篇 电气工程
- 253 篇 信息与通信工程
- 208 篇 生物工程
- 163 篇 光学工程
- 145 篇 生物医学工程（可授...
- 132 篇 控制科学与工程
- 62 篇 电子科学与技术（可...
- 53 篇 机械工程
- 41 篇 化学工程与技术
- 32 篇 材料科学与工程（可...
- 29 篇 仪器科学与技术
- 25 篇 安全科学与工程
498 篇 理学
- 234 篇 数学
- 227 篇 生物学
- 185 篇 物理学
- 80 篇 统计学（可授理学、...
- 39 篇 化学
- 34 篇 系统科学
215 篇 医学
- 199 篇 临床医学
- 85 篇 基础医学(可授医学...
- 61 篇 药学(可授医学、理...
- 29 篇 公共卫生与预防医...
209 篇 管理学
- 140 篇 图书情报与档案管...
- 84 篇 管理科学与工程(可...
- 34 篇 工商管理
43 篇 农学
- 43 篇 作物学
30 篇 法学
- 27 篇 社会学
18 篇 教育学
- 18 篇 教育学
13 篇 经济学
3 篇 军事学
1 篇 艺术学

主题

141 篇 machine learning
122 篇 deep learning
116 篇 image processing
108 篇 pattern recognit...
70 篇 feature extracti...
64 篇 convolutional ne...
57 篇 image segmentati...
46 篇 face recognition
45 篇 computer vision
41 篇 artificial intel...
39 篇 support vector m...
36 篇 image recognitio...
34 篇 image classifica...
31 篇 neural networks
25 篇 training
24 篇 object detection
24 篇 accuracy
22 篇 machine learning...
22 篇 object recogniti...
21 篇 image enhancemen...

机构

6 篇 institute of ima...
5 篇 centre for inter...
5 篇 chitkara univers...
5 篇 univ south dakot...
4 篇 indian statistic...
4 篇 university of ca...
4 篇 national researc...
4 篇 boston universit...
3 篇 dept. of compute...
3 篇 shanghai jiao to...
3 篇 peter the great ...
3 篇 natl. lab. of pa...
3 篇 technische unive...
3 篇 graphic era deem...
3 篇 bangalore
3 篇 department of co...
2 篇 university of sc...
2 篇 université laval...
2 篇 department of cs...
2 篇 italian inst tec...

作者

6 篇 santosh k. c.
5 篇 yang jie
4 篇 gennaro claudio
4 篇 ma songde
4 篇 falchi fabrizio
4 篇 stan sclaroff
4 篇 cheng h.d.
4 篇 cosimo distante
3 篇 wendling laurent
3 篇 frontoni emanuel...
3 篇 guimaraes silvio...
3 篇 battiato sebasti...
3 篇 giovanni m. fari...
3 篇 anon
3 篇 santosh k.c.
3 篇 hegadi ravindra ...
3 篇 marco leo
3 篇 ozawa shinji
3 篇 hossain syed akh...
3 篇 maier-hein klaus

语言

1,463 篇 英文
58 篇 其他
43 篇 中文
2 篇 土耳其文

检索条件"任意字段=1st International Conference on Image Processing Machine Learning and Pattern Recognition"

共 1528 条记录，以下是801-810 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：

Boosting sparsity-induced autoencoder: A novel sparse feature ensemble learning for image classification 1st

Boosting sparsity-induced autoencoder: A novel sparse featur...

引用

1st Chinese conference on pattern recognition and Computer Vision (PRCV)

作者： Shi, Rui Ji, Jian Zhang, Chunhui Miao, Qiguang Xidian Univ Sch Comp Sci & Technol Xian 710071 Shaanxi Peoples R China

ISBN: (纸本)9783030033378

As a kind of unsupervised learning model, the autoencoder is usually adopted to perform the pretraining to obtain the optimal initial value of parameter space, so as to avoid the local minimality that the nonconvex problem may fall into and gradient vanishment of the process of back propagation. However, the autoencoder and its variants have not taken the statistical characteristics and domain knowledge of the train set and also lost plenty of essential representaions learned from different levels when it comes to image processing and computer vision. In this article, we firstly add a sparsity-induced layer into the autoencoder to exploit and extract more representative and essential features exist in the input and then combining the ensemble learning mechanism, we propose a novel sparse feature ensemble learning method, named Boosting sparsity-induced autoencoder, which could make full use of hierarchical and diverse features, increase the accuracy and the stability of a single model. The classification results on different data sets illustrated the effectiveness of our proposed method.

关键词： Sparse representation sparsity-induced mechanism image denoising image classification

来源：评论

学校读者我要写书评

暂无评论

Modified Gabor Filter (MGF) image Enhancement Approach for Early Detection of Lung Cancer 1st

Modified Gabor Filter (MGF) Image Enhancement Approach for E...

引用

1st international conference on Data Science, machine learning and Applications, 2019

作者： Avinash, S. Manjunath, K. Senthil Kumar, S. SDM Institute of Technology Ujire Mangaluru India Tagore Institute of Engineering and Technology ChennaiTamil Nadu India

ISBN: (纸本)9789811514197

Lung cancer continues to be the foremost cause of death in both women and men. Worldwide, lung cancer kills over 1 million peoples a year. The major cause of lung cancer is smoking. In India each year it is estimated that about 80% of male lung cancer deaths and 70% of lung cancer deaths are caused by smoking. Undoubtedly, lung cancer is a major threat to human beings and also a widespread disease which constitutes a major public health problem. Other possible factors for lung cancer are increased air pollution by dusts and gases released by industry, automobile traffic etc. Hence, lung cancer detection is one of the major needs of the day. Several researchers developed image processing Techniques (IPT) for the detection of Lung Cancer [1–8]. Earlier researchers employed the methods like Discrete Cosine Transform (DCT), Auto Enhancement Algorithm (AEA), Fast Fourier Transform (FFT), for image enhancement. These approaches are time consuming and less accurate. Some of the researchers are also used Kalman Filters, Hessian Based Filters (HBF), but these filters have drawbacks like, varying contrast;poor and non-uniform response for images of varying sizes [4, 7]. Some of other researchers used interpolation techniques, which is complex and time consuming [8]. So, to overcome the drawbacks of these earlier approaches, a new image enhancement technique is proposed with modifications in Gabor Filters which will help in early and efficient detection of lung cancer. This Modified Gabor Filter (MGF) approach has been validated using CT (Computer Tomography) and X-ray lung images which are collected from a hospital and they are analysed. The results obtained are comparable with real time analysis of medical practitioners. Hence, this new technique for image Enhancement using MGF Approach can be employed for early detection of lung cancer and this technique is also suitable for development of new medical equipment’s for better detection of lung cancer. © 2020, Springer Nature

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Transfer learning of a Neural Network Using Deep learning to Perform Face recognition 1

Transfer Learning of a Neural Network Using Deep Learning to...

引用

1st international conference on Electrical, Communication and Computer Engineering, ICECCE 2019

作者： Khan, Suleman Ahmed, Ehtasham Javed, M. Hammad Shah, Syed A. A. Ali, Syed Umaid Bahria University Islamabad Campus Dept. of Electrical Engineering Islamabad Pakistan

ISBN: (纸本)9781728138251

Deep learning can be used to solve different problems in image analysis and pattern recognition. Face recognition is it's one of the applications. The use of face recognition to solve different social problems like personal authentication and security is increasing rapidly. In past different face recognition techniques have been introduced like Fisherfaces, Eigenfaces, and LBPH. These methods have low accuracy, so neural networks are used. The deep learning based neural networks are the most accurate. The parameters of the network can be tuned to achieve high accuracy. Face recognition requires a data base of individuals to train a neural network using deep learning. The trained network is then capable of recognition. The framework of the facial recognition process using transfer learning of the pre-trained neural network is described in this paper. We have used AlexNet for recognition which is a pre-trained convolutional neural network. Transfer learning of this pre-trained network has given accuracy of 97.95%. It can be used to classify 1000 different people. For recognition purpose, it requires a large database at least one thousand images per class. The accuracy is although high as compared with techniques mentioned above. © 2019 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Cockpit of Measures for image Quality Assessment in Digital Film Restoration 2nd

A Cockpit of Measures for Image Quality Assessment in Digita...

引用

2nd international Workshop on Recent Advances in Digital Security: Biometrics and Forensics, BioFor 2019, 1st international Workshop on pattern recognition for Cultural Heritage, PatReCH 2019, 1st international Workshop eHealth in the Big Data and Deep learning Era, e-BADLE 2019, international Workshop on Deep Understanding Shopper Behaviors and Interactions in Intelligent Retail Environments, DEEPRETAIL 2019 and Industrial session held at the 20th international conference on image Analysis and processing, ICIAP 2019

作者： Plutino, Alice Lecca, Michela Rizzi, Alessandro Dip. di Informatica Milano Università degli Studi di Milano Milan Italy Fondazione Bruno Kessler ICT Center Trento Italy

ISBN: (纸本)9783030307530

We present an alternative approach for the quality assessment of the digital restoration of a degraded film. Instead of summarizing the film quality by an unique value, here we propose a set of basic measures that account for different film visual features. These measures describe over time global and local properties of the film, like brightness, contrast, color distribution entropy, color variations and perceptual intra-frame color changes. They are relevant to estimate the level of readability of the visual content of the film and to quantify the perceptual differences between the original and restored film. The measures proposed here are viewed as the parameters showed in a car or airplane cockpit and necessary to control the machine status and performance. The idea of cockpit would like to contribute to the automation of the digital restoration process and of its evaluation that are currently still performed for the most part manually by video editors and curators and thus often biased by subjective issues. © 2019, Springer Nature Switzerland AG.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Robust learning and recognition of Visual patterns in Neuromorphic Electronic Agents 1

Robust Learning and Recognition of Visual Patterns in Neurom...

引用

1st IEEE international conference on Artificial Intelligence Circuits and Systems (AICAS)

作者： Liang, Dongchen Kreiser, Raphaela Nielsen, Carsten Qiao, Ning Sandamirskaya, Yulia Indiveri, Giacomo Univ Zurich Inst Neuroinformat Zurich Switzerland Swiss Fed Inst Technol Zurich Switzerland

ISBN: (纸本)9781538678848

Mixed-signal analog/digital neuromorphic circuits are characterized by ultra-low power consumption, real-time processing abilities, and low-latency response times. These features make them promising for robotic applications that require fast and power-efficient computing. However, the unavoidable variance inherently existing in the analog circuits makes it challenging to develop neural processing architectures able to perform complex computations robustly. In this paper, we present a spiking neural network architecture with spike-based learning that enables robust learning and recognition of visual patterns in noisy silicon neural substrate and noisy environments. The architecture is used to perform pattern recognition and inference after a training phase with computers and neuromorphic hardware in the loop. We validate the proposed system in a closed-loop hardware setup composed of neuromorphic vision sensors and processors, and we present experimental results that quantify its real-time and robust perception and action behavior.

关键词： Neuromorphic computing noisy spiking neural networks robust object recognition unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A Classroom Atmosphere Management System for Analyzing Human Behaviors in Class Activities 1

A Classroom Atmosphere Management System for Analyzing Human...

引用

1st international conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Ku, Yu-Te Yu, Han-Yen Chou, Yi-Chi Inst Informat Ind Digital Inst Taipei Peoples R China

ISBN: (纸本)9781538678220

Deep learning can considerably improve the processing of human behavior signals. This paper presents a system that used computer vision processing of human behavior signals to analyze the behaviors of students in class activities. ClassFu system can be used in physical and online teaching environments. It used image sensors to capture student class behaviors, analyzing classroom atmosphere and the level of teacher-student interaction. The system presents objective data on a teaching setting, which can be used to assess students' learning conditions more effectively and enhance teacher-student interactions.

关键词： Deep learning ClassFu system human behavior analysis gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Equipment Condition Identification Based on Telemetry Signal Clustering 14th

Equipment Condition Identification Based on Telemetry Signal...

引用

14th international conference on pattern recognition and Information processing (PRIP)

作者： Eroma, Alexander Dukhounik, Andrei Aksenov, Oleg Marushko, Yauheni Octon Technol 25-203 Yanki Kupaly St Minsk 220030 BELARUS Belarusian State Univ Informat & Radioelect 6 P Brovki St Minsk 220013 BELARUS Natl Acad Sci Belarus United Inst Informat Problems St Surganova 6 Minsk 220012 BELARUS

ISBN: (纸本)9783030354305;9783030354299

This paper deals with the problem of pattern detection in telemetry data, in particular, the approach of automatic machine state detection based on the vibration signal proposed. The approach based on the analysis of the signal via clustering. The paper provides basic information about telemetry data analysis, vibration data analysis, and machine condition monitoring. Also, an overview of cluster analysis methods provided. The proposed approach based on clustering of objects represented with feature set extracted from vibration signals. Given the explanation of the technique and illustrative example of the application of the proposed approach applied to vibration data provided by SmartEdge Agile device for industrial electric motor considered.

关键词： Signal processing Vibration signals Clustering Unsupervised learning Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

The Vending Shopper Science Lab: Deep learning for Consumer Research 2nd

The Vending Shopper Science Lab: Deep Learning for Consumer ...

引用

作者： Allegrino, Fioravante Gabellini, Patrizia Di Bello, Luigi Contigiani, Marco Placidi, Valerio Sogeda S.R.L. Via Volturno 10 San Giovanni TeatinoChieti66020 Italy Grottini Lab S.R.L. Via Santa Maria in Potenza Porto Recanati62017 Italy

ISBN: (纸本)9783030307530

To understand human behavior, a fundamental aspect is the analysis of the face and movement. This aspect is particularly important in the context of sales, where to know the shopper also means to guide purchases. A major challenge for vending environment is to predict the shopper behavior, with the aim to influence and increase purchases. In this ambit, vending machine industry is actually an interesting and growing data-driven marketing area of research. In this context, the aim of this paper is to propose an innovative architecture that is able to integrate face and movement understanding in a common strategy for real time consumer modeling. The vending machine and the decision support system process multimedia data to smartly respond with dynamic pricing and product proposal to the particular shopper which is in front of a vending machine. The aim is to build an intelligent vending machine which in real time is able to suitably propose products to a labelled shopper. The results come from real environments vending lab with 30 locations and about 1 million consumers in Italy, and have the aim to demonstrate the good performances and high efficiency of our solution in recognizing the age and the gender of consumer and different interactions with the vending machine. © 2019, Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Restricted Boltzmann machine as image Pre-processing Method for Deep Neural Classifier 1

Restricted Boltzmann Machine as Image Pre-processing Method ...

引用

1st international conference on Societal Automation (SA)

作者： Sobczak, Szymon Kapela, Rafal Poznan Univ Tech Poznan Poland

ISBN: (纸本)9781728133454

The paper presents a novel approach to image preprocessing for feature extraction that is designed for reduction of dimensionality of the classifier which is in this case the convolutional neural network (CNN). The proposed method uses Restricted Boltzmann machine(RBM) as an Aggregation Method (AM) for binary feature descriptors. The assumption of this technique is that the RBM is performing an dimension expansion of the feature space. Also the type of the data undergoes the transformation from binary to floating point. The conventional approach in convolutional neural networks uses as an input the image that consists of one (grayscale) or three channels (RGB). The method presented herein allows to have the number of channels configurable, as it depends on the size of the Restricted Boltzmann machine (RBM). The size of the entire network and its parallel implementation makes the architecture usable in realtime systems with reduced memory size.

关键词： Restricted Boltzmann machine image local binary descriptors aggregation techniques of feature vectors deep learning

来源：评论

学校读者我要写书评

暂无评论

IMPROVING ROBUstNESS TO ADVERSARIAL EXAMPLES BY ENCOURAGING DISCRIMINATIVE FEATURES 26

IMPROVING ROBUSTNESS TO ADVERSARIAL EXAMPLES BY ENCOURAGING ...

引用

26th IEEE international conference on image processing (ICIP)

作者： Agarwal, Chirag Anh Nguyen Schonfeld, Dan Univ Illinois Chicago IL 60607 USA Auburn Univ Auburn AL 36849 USA

ISBN: (数字)9781538662496

ISBN: (纸本)9781538662496

Deep neural networks (DNNs) have achieved state-of-theart results in various pattern recognition tasks. However, they perform poorly on out-of-distribution adversarial examples i.e. inputs that are specifically crafted by an adversary to cause DNNs to misbehave, questioning the security and reliability of applications. In this paper, we hypothesize interclass and intra-class feature variances to be one of the reasons behind the existence of adversarial examples. Additionally, learning low intra-class and high inter-class feature variance help classifiers learn decision boundaries that are more compact and leave less inter-class low-probability "pockets" in the feature space, i.e. less room for adversarial perturbations. We achieve this by imposing a center loss [1] in addition to the regular softmax cross-entropy loss while training a DNN classifier. Intuitively, the center loss encourages DNNs to simultaneously learn a center for the deep features of each class, and minimize the distances between the intra-class deep features and their corresponding class centers. Our results on state-of-the-art architectures tested on MNIst, CIFAR-10, and CIFAR-100 datasets confirm our hypothesis and highlight the importance of discriminative features in the existence of adversarial examples.

关键词： Adversarial machine learning Robustness Defenses Deep learning

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153页 << < 77 78 79 80 81 82 83 84 85 86 > >>

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：