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2461-2470 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：

A 1.12nJ/Pixel High-Accuracy and Memory-Efficient Real-Time Object Detection Processor for Neuromorphic Vision Sensors

A 1.12nJ/Pixel High-Accuracy and Memory-Efficient Real-Time ...

引用

IEEE Asian conference on Solid-State Circuits (ASSCC)

作者： Zehao Li Wenhao Lu Yuncheng Lu Junying Li Yucen Shi Yuanjin Zheng Tony Tae-Hyoung Kim Nanyang Technology University Singapore

ISBN: (数字)9798350376326

ISBN: (纸本)9798350376333

Neuromorphic vision sensors (NVSs) [1], which generate an event only when a pixel’s log intensity changes, feature low data redundancy and transmission latency, making them increasingly popular in various edge applications, such as traffic monitoring and object detection. Compared to event-by-event processing paradigms that require the processor to be always-on [2], frame-based counterparts are more power-efficient, as they keep the processor in an idle state during frame construction, resulting in a reduced signal toggling rate. However, as NVSs continue to evolve, the increasing resolution necessitates a substantial amount of on-chip memory to hold the reconstructed event-based binary image (EBBI), as depicted in Fig. 1 (top). Furthermore, most existing systems are suited only for stationary scenes, as moving NVSs introduce background noise [3]. In addition, prior object detection systems based on deep neural networks (DNN) or connected component labeling (CCL) suffer from significant memory overhead and long processing latency due to large model sizes and high computational intensity.

关键词： Neuromorphics Redundancy Object detection artificial neural networks Vision sensors Real-time systems System-on-chip Solid state circuits Signal resolution Monitoring

来源：评论

学校读者我要写书评

暂无评论

Three-Level Gray-Scale images Segmentation using Non-extensive Entropy

Three-Level Gray-Scale Images Segmentation using Non-extensi...

引用

International conference on Computer Graphics, Imaging and Visualization, CGIV

作者： I. El-Feghi M. Galhoud M.A. Sid-Aadhmed M. Ahmadi Higher Industry Institute Misurata-Libya ECE Department Al-Fateh University Tripoli Libya University of Windsor Windsor Canada

The segmentation of images into meaningful and homogenous regions is a crucial step in many image analysis applications. In this paper, we present a three-level thresholding method for image segmentation. The method is based on maximizing non-extensive entropy. After segmentation, the output image will consist of three homogenous regions, namely, dark, gray and white. The threshold value for each region is decided by maximizing an extended form of Tsallis entropy. To improve the performance of the proposed algorithm, an efficient and computationally fast method for initializing the search for maximum entropy is also presented. Results obtained using the proposed algorithm are compared with those obtained using Shannon entropy.

关键词： Gray-scale image segmentation Entropy Pixel Histograms artificial neural networks Visualization image processing Convergence image analysis

来源：评论

学校读者我要写书评

暂无评论

BatchUp:A Feature Space-Level Multi-Data Mixing Technique for Convolutional neural Network

BatchUp:A Feature Space-Level Multi-Data Mixing Technique fo...

引用

Next Generation Data-driven networks (NGDN), International conference on

作者： Rongxin Li Artificial Intelligence Academy Jilin University Changchun China

ISBN: (数字)9798350388374

ISBN: (纸本)9798350388381

image data is a common data type in life, and the processing of massive image data has become a key factor in ensuring high-performance applications. However, researchers often face problems such as missing data and insufficient annotation when processing these data. In order to solve these problems, data enhancement technology emerged, which effectively expands the data set by transforming or synthesizing original images, providing more possibilities for model training. Among the existing data enhancement methods, they mainly include sample selection strategies and hybrid strategies. Among them, hybrid strategies are widely used, but sample selection strategies are rarely mentioned. This is because the sample selection process is full of unknowns, and it is easy to select mismatched features for mixing, causing the predicted values of the generated samples to be inconsistent with the original samples, making the generated samples become noise, thus degrading the predictive ability of the model. To overcome this challenge, this paper proposes a BatchUp hybrid approach. This method accurately selects and mixes the samples themselves. Since we mix some features in the hidden space, and the hidden space has more dimensional features, we will get more different samples, that is, we can have More information is used for training to ensure that the generated samples are consistent with the original samples in terms of predicted values. This not only solves the problems existing in current data augmentation technology, but also improves the prediction accuracy and generalization ability of the model. Experiments on CIFAR10/100, SVHN using ResNet architectures (including PreActResnet18/34 models) show that BatchUp improves or equals the current state-of-the-art CNN regularizer performance.

关键词： Training Noise Diversity reception Predictive models Data augmentation Data models Convolutional neural networks Next generation networking Faces Overfitting

来源：评论

学校读者我要写书评

暂无评论

image processing-Based Methods to Improve the Robustness of Robotic Gripping

Image Processing-Based Methods to Improve the Robustness of ...

引用

International Symposium on Computational Intelligence and Informatics

作者： Kristóf Takács Renáta Nagyné Elek Tamás Haidegger Antal Bejczy Center for Intelligent Robotics Óbuda Universtiy Budapest Hungary Doctoral School of Applied Informatics and Applied Mathematics Óbuda University Budapest Hungary John von Neumann Faculty of Informatics Óbuda University Budapest Hungary University Research and Innovation Center (EKIK) Óbuda University Budapest Hungary Austrian Center for Medical Innovation and Technology Wiener Neustadt Austria

ISBN: (纸本)9798350398830

image processing techniques are having a huge impact on most fields of robotics and industrial automation. Real-time methods are usually employed in complex automation tasks, assisting with decision making or directly guiding robots and machinery, while post-processing is usually used for retrospective assessment of systems and processes. While artificial intelligence-based image processing algorithms (relying usually on neural networks) are more common nowadays, “classical” image processing methods can also be used effectively for most modern applications. This paper focuses on optical flow-based image processing, proving its efficiency by presenting optical flow-based solutions for modern challenges in different fields of robotics, such as robot-assisted surgery and food processing. The application domain introduced in this paper is based on a smart robotic gripper designed to support automated robot cells in the meat industry. The gripper is capable of slip detection and secure gripping of soft, slippery tissues with the help of the implemented real-time algorithm.

关键词： Training Biomedical optical imaging Automation Service robots image processing Surgery Optical computing

来源：评论

学校读者我要写书评

暂无评论

A novel SoC architecture on FPGA for ultra fast face detection

A novel SoC architecture on FPGA for ultra fast face detecti...

引用

IEEE International conference on Computer Design: VLSI in Computers and Processors, (ICCD)

作者： Chun He Alexandros Papakonstantinou Deming Chen Research Institute of Electronic Science & Tech University of Electronic Science and Technology China Electrical & Computer Engineering University of Illinois Urbana-Champaign IL USA

Face detection is the cornerstone of a wide range of applications such as video surveillance, robotic vision and biometric authentication. One of the biggest challenges in face detection based applications is the speed at which faces can be accurately detected. In this paper, we present a novel SoC (System on Chip) architecture for ultra fast face detection in video or other image rich content. Our implementation is based on an efficient and robust algorithm that uses a cascade of artificial neural Network (ANN) classifiers on AdaBoost trained Haar features. The face detector architecture extracts the coarse grained parallelism by efficiently overlapping different computation phases while taking advantage of the finegrained parallelism at the module level. We provide details on the parallelism extraction achieved by our architecture and show experimental results that portray the efficiency of our face detection implementation. For the implementation and evaluation of our architecture we used the Xilinx FX130T Virtex5 FPGA device on the ML510 development board. Our performance evaluations indicate that a speedup of around 100X can be achieved over a SSE-optimized software implementation running on a 2.4 GHz Core-2 Quad CPU. The detection speed reaches 625 frames per sec (fps).

关键词： Field programmable gate arrays Face detection Computer architecture Parallel processing artificial neural networks Video surveillance Robot vision systems Biometrics Authentication System-on-a-chip

来源：评论

学校读者我要写书评

暂无评论

Crop Disease Detection using CNN Architecture VGG16

Crop Disease Detection using CNN Architecture VGG16

引用

Advances in Computing, Communication and Networking (ICAC2N), International conference on

作者： Sandeep Raj Surinder Kaur Neetu Singh Monica Gupta Department of Artificial Intelligence & Machine Learning Dronacharya College of Engineering Farrukh Nagar Haryana Department of Information Technology Bharati Vidyapeeth’s College of Engineering New Delhi Department of Electronics and Communication Engineering Bharati Vidyapeeth’s College of Engineering New Delhi

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

The Agriculture plays a major part in any nation for economy through the production of various crops and it’s an essential source of income in India. The plant disease is one of the leading task of agriculture. When the infections occur in crops result in reduced quantity and quality of production of crops which will result in economic loss. Therefore, plague needs to be identified as quickly as possible for the healthy production of crops and plants. Various methods and solutions were proposed for crop disease detection by the researchers using image processing, machine learning, and deep learning. The deep learning plays an essential part in the field of image processing using convolution neural networks and their architecture. In this experiment, we have examined the CNN, Transfer learning VGG16 model on the plant-village dataset which was available on the Kaggle. The dataset(records) includes images of various potato, tomato and pepper crops of 15 different classes. The detection was done using the leaf samples. Our goal is to detect the disease in plants with accurate without taking so much time so that people can take care of their plants and apply the appropriate treatment. In future this VGG16 can be used to identify specific objects, animals, plants, and more in a picture. to identify, recognition and classification of image, that will use in many applications. Medical, Banking, Transportations well as Agriculture.

关键词： Deep learning Plant diseases Transfer learning neural networks Crops Transportation Production Computer architecture Agriculture Object recognition

来源：评论

学校读者我要写书评

暂无评论

Implementation of Grey Scale Normalization in Machine Learning & artificial Intelligence for Bioinformatics using Convolutional neural networks

Implementation of Grey Scale Normalization in Machine Learni...

引用

International conference on Inventive Computation Technologies (ICICT)

作者： Divya Kothari Mayank Patel Ajay Kumar Sharma Geetanjali Institute of Technical Studies Udaipur

ISBN: (数字)9781728185019

ISBN: (纸本)9781728185026

Machine Learning is a trending field nowadays and is very well known as an application of artificial Intelligence (AI). Machine learning makes use of secure arithmetical algorithms to construct computers assignment in a constructive way without being unequivocally programmed. The algorithms acquire freedom of a participated value and estimate output for this by utilizing definite arithmetical methods. The key function of machine learning is to create smart machines that can visualize and work related to human beings. artificial Intelligence has been witnessing a massive improvement in bridging the gap among the capabilities of humans and technologies. Similarly, one of the characteristics of the field were tried to combine the outstanding effects. A Convolution neural Network (CNN) is a sort of Deep Learning algorithm which can obtain an input image, assign consequence to different aspects in the image and capable to differentiate one from the other. The pre-processing requirement in a CNN is lesser as compared to other classification algorithms. CNN has the capability to find out these filter's characteristics. Bioinformatics is a term that is a mixture of two terms bio and informatics. Bio means associated with biology and informatics means in a sequence of information. Thus bioinformatics is an area that deals with handing out and accepting biological statistics using the computational and arithmetical approaches. Machine Learning has added up to of applications in the area of bioinformatics. Machine Learning finds its submission in the subsequent subfields of bioinformatics. The aim of this article is to perform a grayscale normalization of a selected image and thereafter to reduce the effect of illumination differences. Normalization is considered so that CNN works in a faster manner. Different models are available but Keras model is selected to perform this task. Keras supports the style of data preparation for image statistics via the image Data Generator gro

关键词： Machine learning algorithms Biological system modeling Computational modeling Machine learning Generators Classification algorithms Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

image processing technique for segmenting microstructural porosity of laser-welded thermoplastics

Image processing technique for segmenting microstructural po...

引用

IEEE International conference on Electronics, Circuits and Systems (ICECS)

作者： Karl Leboeuf Iman Makaremi Roberto Muscedere Majid Ahmadi Department of Electrical and Computer Engineering University of Windsor Windsor ONT Canada

Plastics are used in a truly vast number of applications, and research is continously carried out to improve every aspect of the plastics industry. A recent study of laser transmission welding [1] required cross-sectional images of the weld's microstructure to be analyzed for the presence of pores, which are tiny bubbles that may form during the weld process. It is believed that the number and size of pores may be indicative of the weld strength [1]. The current state of the art for detecting these pores involves manually drawing a contour around each one; a laborious process given that a typical sample may have hundreds-to-thousands of pores. This paper presents a segmentation system for classifying the pixels of a microstructural image of a thermoplastic laser weld as either belonging to a pore or the background. The algorithm is robust in terms of dealing with noise from flbreglass strands, cloudy pores, and varying exposure time. On average, it is estimated that the proposed algorithm is able to correctly classify pores at a rate of approximately 90% without requiring any user intervention.

关键词： image segmentation Welding artificial neural networks Training Humans Noise Neurons

来源：评论

学校读者我要写书评

暂无评论

Research on Fault Diagnosis and Parameter Identification of Bidirectional LLC Resonant Converter Based on Data Driven

Research on Fault Diagnosis and Parameter Identification of ...

引用

image processing, Electronics and Computers (IPEC), Asia-Pacific conference on

作者： Xiaorui Zhang Shuo Jiang Pingxin Ma Dongyang Luo Tian Zhao Fengping He China Academy of Space Technology(CAST) Institute of Telecommunication and Navigation Satellites Beijing China

ISBN: (数字)9798350374407

ISBN: (纸本)9798350374414

At present, few people have studied the fault diagnosis of bidirectional LLC resonant converters. In order to promote the development of digital and intelligent fault diagnosis of power converters, this article analyzes the structural and parametric fault characteristics of bidirectional LLC resonant converters, designs structural fault diagnosis algorithms based on Support Vector Machine (SVM) and Random Forest (RF), and compares the diagnostic results of the two algorithms. Among them, the accuracy of random forest fault diagnosis is $100 \%$, the accuracy of SVM fault diagnosis is $98.58 \%$, the accuracy of RF fault diagnosis is higher, and the fault diagnosis speed is faster; At the same time, a bidirectional LLC resonant converter resonant capacitor parameter identification algorithm based on Extreme Learning Machines (ELM) and Deep neural Network (DNN) was studied. As a deep learning algorithm, DNN has an identification error of less than $5 \%$ and significantly better performance than ELM. The data-driven bidirectional LLC resonant converter fault diagnosis and parameter identification carried out in this article have achieved good results, laying a foundation for subsequent engineering applications.

关键词： Fault diagnosis Support vector machines Radio frequency Parameter estimation Accuracy Resonant converters artificial neural networks Prediction algorithms Circuit faults Random forests

来源：评论

学校读者我要写书评

暂无评论

Efficient FPGA implementation of a knowledge-based automatic speech classifier 1

引用

2nd International conference on Embedded Software and Systems, ICESS 2005

作者： Siniscalchi, Sabato M. Gennaro, Fulvio Vitabile, Salvatore Gentile, Antonio Sorbello, Filippo 90128 Palermo Italy Dipartimento di Biotecnologie Mediche e Medicina Legale Università di Palermo Via del Vespro 90127 Palermo Italy Center for Signal and Image Processing School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA 30332 United States 90128 Palermo Italy

ISBN: (数字)9783540322979

ISBN: (纸本)3540308814

Speech recognition has become common in many application domains, from dictation systems for professional practices to vocal user interfaces for people with disabilities or hands-free system control. However, so far the performance of Automatic Speech Recognition (ASR) systems are comparable to Human Speech Recognition (HSR) only under very strict working conditions, and in general far lower. Incorporating acoustic-phonetic knowledge into ASR design has been proven a viable approach to rise ASR accuracy. Manner of articulation attributes such as vowel, stop, fricative, approximant, nasal, and silence are examples of such knowledge. neural networks have already been used successfully as detectors for manner of articulation attributes starting from representations of speech signal frames. In this paper an optimized digital Knowledge-based Automatic Speech Classifier for real-time applications is implemented on FPGA using six attribute scoring Multi-Layer Perceptrons (MLP). Digital MLP key features are a virtual neuron architecture and use of sinusoidal activation functions for the hidden layer. Implementation results on FPGA show that use of sinusoidal activation functions decrease hardware resource usage of more than 50% for slices, FFs, LUTs and more than 35% for FPGA RAM blocks when compared with the standard sigmoid-based neuron implementation. Furthermore, neuron virtualization allows for a significant decrease of concurrent memory access, resulting in improved performance for the entire attribute scoring module. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Speech recognition

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 << < 243 244 245 246 247 248 249 250 251 252 > >>

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：