检索结果-内蒙古大学图书馆

Watch You under Low-Resolution and Low-Illumination: Face Enhancement via Bi-Factor Degradation Decoupling

IEEE Transactions on Circuits and Systems for Video Technology 2024年第5期34卷 3481-3495页

作者： Ding, Xin Wang, Zheng Fang, Jing Shu, Zhenyu Hu, Ruimin Lin, Chia-Wen NingboTech University School of Computer and Data Engineering Ningbo315100 China Wuhan University National Engineering Research Center for Multimedia Software School of Computer Wuhan430072 China National Tsing Hua University Department of Electrical Engineering The Institute of Communications Engineering Hsinchu300044 Taiwan

Face enhancement aims to improve low-quality face images to a higher-quality level. However, in real-world nighttime scenes, complex degradation factors often affect these images, making it challenging to preserve important facial details. Existing image enhancement algorithms typically focus on independently conducting image super-resolution and brightness enhancement, assuming a fixed degradation level based on simulated training datasets. Nonetheless, real nighttime scenes involve complex degradation processes, where degradation factors dynamically and variably manifest. Therefore, achieving effective face enhancement in such scenarios is particularly daunting. This work analyzes and unveils the multiple factors of low resolution and low illumination during degradation. Based on this analysis, we propose a Bi-factor Degradation Decoupling network. Our method leverages a decoupling network to generate qualitative and quantitative features corresponding to each factor's degradation degree in the low-quality environment. These features are then combined with robust facial feature constraints to recover the details of low-quality faces. Extensive experiments demonstrate that our method surpasses state-of-the-art approaches in both enhancement and face super-resolution. © 1991-2012 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Privilege negotiation agents for distributed authorisation on world wide web

Privilege negotiation agents for distributed authorisation o...

引用

作者： Au, Richard Yao, Ming Looi, Mark Information Security Research Centre School of Software Engineering and Data Communications Queensland University of Technology QLD 4001 Australia

ISBN: (纸本)0769519318

Privilege Negotiation Agents migrate from the security servers of different adminstrative domains on the Internet to the user's Secure Client Agent Environment. They work cooperatively for trust establishment and authorisation in an automated way. Agent communication protocols are expressed through Knowledge Query and Manipulation Language(KQML). Security issues for interaction between agents are discussed. The user-centred approach enables a user to enforce his own privacy policies during the privilege negotiation process. © 2003 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identifying critical components during information security evaluations

Identifying critical components during information security ...

引用

作者： Rae, Andrew Fidge, Colin Invensys Rail Systems Australia Brisbane Technology Park QLD 4113 Australia Queensland University of Technology School of Software Engineering and Data Communications QLD 4001 Australia Invensys Rail Systems Australia Department of Computer Science School of Software Engineering and Data Communications Queensland University of Technology

Electronic communications devices intended for government or military applications must be rigorously evaluated to ensure that they maintain data confidentiality. High-grade information security evaluations require a detailed analysis of the device's design, to determine how it achieves necessary security functions. In practice, such evaluations are labour-intensive and costly, so there is a strong incentive to find ways to make the process more efficient. In this paper we show how well-known concepts from graph theory can be applied to a device's design to optimise information security evaluations. In particular, we use end-to-end graph traversals to eliminate components that do not need to be evaluated at all, and minimal cutsets to identify the smallest group of components that needs to be evaluated in depth. Copyright © 2005, Australian Computer Society Inc.

关键词： Information analysis

来源：评论

学校读者我要写书评

暂无评论

Mining rough association from text documents for web information gathering

引用

作者： Li, Yuefeng Zhong, Ning School of Software Engineering and Data Communications Queensland University of Technology Brisbane QLD 4001 Australia Department of Information Engineering Maebashi Institute of Technology Maebashi 371-0816 Japan

ISBN: (纸本)9783540716624

It is a big challenge to guarantee the quality of association rules in some application areas (e.g., in Web information gathering) since duplications and ambiguities of data values (e.g., terms). Rough set based decision tables could be efficient tools for solving this challenge. This paper first illustrates the relationship between decision tables and association mining. It proves that a decision rule is a kind of closed pattern. It also presents an alternative concept of rough association rules to improve the quality of discovered knowledge in this area. The premise of a rough association rule consists of a set of terms (items) and a weight distribution of terms (items). The distinct advantage of rough association rules is that they contain more specific information than normal association rules. This paper also conducts some experiments to compare the proposed method with association rule mining and decision tables;and the experimental results verify that the proposed approach is promising. © Springer-Verlag Berlin Heidelberg 2007.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Debug-tool for embedded real time systems

Debug-tool for embedded real time systems

引用

International Conference on Computer as a Tool (EUROCON 2005)

作者： Langer, J Koppenberger, K Sulzbachner, C Nestler, T IEEE Austria School of Electrical Engineering Technical University of Vienna Austria University of Applied Sciences of Upper Austria School of Hardware/Software Systems Engineering Austria CDE Communications Data Engineering GmbH 4222 Luftenbergj Im Fall 21 Austria

ISBN: (纸本)142440049X

In this paper we present the computer as a debug-tool for embedded real time systems. The debug-tool has a graphical user interface to set and view parameters. It also has a communication channel based on the serial interface to communicate with the appropriate hardware. The hardware consists of a FPGA with a debug-interface. In the FPGA a softcore processor is implemented. software and hardware latencies shall be measured with the debug-interface, to rind sophisticated timing problems, which often cause problems in embedded control applications. The debug interface monitors all states and timings of the hardware and software under real time conditions. The computer can configure the debug-interface and set trigger-points to trigger special events, e.g. exceeded timing latencies for interrupt execution.

关键词： computer engineering debug-tool monitoring embedded systems

来源：评论

学校读者我要写书评

暂无评论

Probabilistic logic under uncertainty 07

Probabilistic logic under uncertainty

引用

Proceedings of the thirteenth Australasian symposium on Theory of computing - Volume 65

作者： Audun Jøsang School of Software Engineering and Data Communications Brisbane Australia

ISBN: (纸本)9781920682460

Probabilistic logic combines the capability of binary logic to express the structure of argument models with the capacity of probabilities to express degrees of truth of those arguments. The limitation of traditional probabilistic logic is that it is unable to express uncertainty about the probability values themselves. This paper provides a brief overview subjective logic which is a probabilistic logic that explicitly takes uncertainty about probability values into account. More specifically, we describe equivalent representations of uncertain probabilities, and their interpretations. Subjective logic is directly compatible with binary logic, probability calculus and classical probabilistic logic. The advantage of using subjective logic is that real world situations can be more realistically modelled, and that conclusions more correctly reflect the ignorance and uncertainties about the input arguments.

关键词： belief theory beta opinion probabilistic logic subjective logic uncertainty dirichlet

来源：评论

学校读者我要写书评

暂无评论

Mining world knowledge for analysis of search engine content

引用

Web Intelligence and Agent Systems 2007年第3期5卷 233-253页

作者： King, John D. Li, Yuefeng Tao, Xiaohui Nayak, Richi School of Software Engineering and Data Communications Queensland University of Technology QLD 4001 Australia

Little is known about the content of the major search engines. We present an automatic learning method which trains an ontology with world knowledge of hundreds of different subjects in a three-level taxonomy covering the documents offered in our university library. We then mine this ontology to find important classification rules, and then use these rules to perform an extensive analysis of the content of the largest general purpose internet search engines in use today. Instead of representing documents and collections as a set of terms, we represent them as a set of subjects, which is a highly efficient representation, leading to a more robust representation of information and a decrease of synonymy.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Handwriting Recognition 1

引用

丛书名： Studies in Fuzziness and Soft Computing

1000年

作者： Zhi-Qiang Liu Richard Buse Jinhai Cai

ISBN: (数字)9783540448501

ISBN: (纸本)9783540401773;9783642072802

Over the last few decades, research on handwriting recognition has made impressive progress. The research and development on handwritten word recognition are to a large degree motivated by many application areas, such as automated postal address and code reading, data acquisition in banks, text-voice conversion, security, etc. As the prices of scanners, com puters and handwriting-input devices are falling steadily, we have seen an increased demand for handwriting recognition systems and software pack ages. Some commercial handwriting recognition systems are now available in the market. Current commercial systems have an impressive performance in recognizing machine-printed characters and neatly written texts. For in stance, High-Tech Solutions in Israel has developed several products for container ID recognition, car license plate recognition and package label recognition. Xerox in the U. S. has developed TextBridge for converting hardcopy documents into electronic document files. In spite of the impressive progress, there is still a significant perfor mance gap between the human and the machine in recognizing off-line unconstrained handwritten characters and words. The difficulties encoun tered in recognizing unconstrained handwritings are mainly caused by huge variations in writing styles and the overlapping and the interconnection of neighboring characters. Furthermore, many applications demand very high recognition accuracy and reliability. For example, in the banking sector, although automated teller machines (ATMs) and networked banking sys tems are now widely available, many transactions are still carried out in the form of cheques.

关键词： Artificial Intelligence Learning & Instruction Pattern Recognition Natural Language Processing (NLP) Applications of Mathematics Complexity

来源：评论

学校读者我要写书评

暂无评论

Topic-oriented mining and reasoning

Topic-oriented mining and reasoning

引用

2005 International Conference on Active Media Technology, AMT 2005

作者： Li, Yuefeng Zhong, Ning Yao, Y.Y. School of Software Engineering and Data Communications Queensland University of Technology Brisbane QLD 4001 Australia Department of Systems and Information Engineering Maebashi Institute of Technology Japan Department of Computer Science University of Regina Canada

ISBN: (纸本)0780390350

The discovery of the association between terms and a specified topic is a difficult task. A new data mining technique, topic-oriented mining and reasoning, is presented for this task. The technique consists of two threads: pattern mining and pattern reasoning. Pattern mining means the automatic discovery of interesting user topic models. A novel topic structure is presented for this thread. Pattern reasoning means the utilization and maintenance of the interesting user topic models to determine if an input data is relevant to the specified topic. The innovation for this thread is the use of Meta-knowledge for the discovered knowledge. In this way the system can trace errors to update inadequate subtopics in the user topic model. The experimental results show that all objectives we expect for the topic-oriented model are achievable. © 2005 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Local Cluster Neural Network On-chip Training

Local Cluster Neural Network On-chip Training

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Liang Zhang J. Sitte School of Software Engineering and Data Communications Queensland University of Technology Australia

The local cluster neural network is a feedforward RBF network that has been implemented in analogue neural net chip. The LCNN chip can be trained by chip-in-the-loop training and this training method has been demonstrated to work efficiently. In order to increase the functionality of LCNN chip, we proposed on-chip training for the LCNN chip. In this paper, we describe two training algorithms -Gradient Descent and Probabilistic Random Weight Change, which are used in LCNN on-chip training simulations. We also present the experiment results from the simulations in multidimensional function approximation. The training convergence is investigated and analyzed. The circuite signal flow chart for these two algorithms are designed.

关键词： Neural networks Network-on-a-chip Feedforward neural networks Circuit simulation Radial basis function networks Multidimensional systems Function approximation Convergence Flowcharts Signal design

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：