Applications
As only verbs can not make a language, computational verbs must be used together with computational nouns in engineering applications. The known industrial and commercial applications of computational verbs are listed as follows.• Physical Linguistic Vision Technologies: Digital image processing embedded with computational cognition.
• Computational Verb Controllers: Controlling with dynamic experiences.
• Background and shadow removal.
Theories
The early work of computational verb theory can be found in the following book
• 1-56072-971-6:: T. Yang, Advances in Computational Verb Systems, Huntington, NY: Nova Science Publishers, Inc., May 2001.
The primary structure of physical linguistics can be found in the following books
• 0-9721212-1-8:: T. Yang, Computational Verb Theory: From Engineering, Dynamic Systems to Physical Linguistics. Oct. 02, Amazon $77.99 (Library of Congress Online Catalog. CALL NUMBER: P281 .Y365 2002 CALL NUMBER: P281 .Y365 2002 FT MEADE).
• 0-9721212-2-6:: T. Yang, Fuzzy Dynamic Systems and Computational Verbs Represented by Fuzzy Mathematics, Sept. 03, Amazon $57.99 (Library of Congress Online Catalog. CALL NUMBER: P281 .Y366 2003).
The latest results of computational verb theory and physical linguistics can be found in the following book
• 0-9721212-3-4:: T. Yang, Physical Linguistics:measurable linguistics and duality between universe and cognition, Dec. 04, Amazon $77.99 (Library of Congress Online Catalog. CALL NUMBER: P138 .Y36 2004).
The First Textbook to Include Computational Verb Controllers
INTRODUCTION TO FUZZY
SYSTEMS,
Guanrong Chen(CITY UNIVERSITY OF HONG KONG, KOWLOON) and
Trung Tat Pham
(DICENTRAL CORPORATION, HOUSTON, TEXAS, USA), ISBN:1-58488-531-9.
Chapter 7: Computational Verb Fuzzy Controllers
• Computational Verbs and Verb Numbers
• Verb Rules and Verb Inference
• Computational Verb-Based Fuzzy PID Controllers
See details in the flyer.
Preview this book.
College Courses with Computational Verbs
• Dr. G. Chen, EE 64152 - Introduction to Fuzzy Informatics and Intelligent Systems [link] [cached]
• Dr. Mahir Sabra, EELE 6306: Intelligent Control [link] [cached]
• Professor Tao Yang, Computational Methodologies in Intelligent Systems, Department of Electronic Engineering, Xiamen University.
•
•
A Brief History of Computational Verb Theory
• The beginning of computational verb was at the end of 1997 when Tao Yang,
then a visiting scholar in the Department of Electrical Engineering and Computer
Sciences, University of California at Berkeley, published two department technical
reports addressing how to use dynamic theory to model verbs in natural languages.
The scanning images of these two technical reports are shown as follow.


• In 2000, the first book on the topic of “Computing with Words” dedicated a long chapter to computational verbs.


• In 2001, the first book on computational verbs,
“Advances in Computational Verb Systems”, published.

• In 2002, Computational Verb Theory was established in the book entitled “Computational Verb Theory” and the concept of physical linguistics was mentioned the first time.

• In 2004, the theory of physical linguistics was established and the concept of the Unicogse was initiated in the book entitled “Physical Linguistics: Measurable Linguistics and Duality Between Universe and Cognition”.
• In 2004, the first commercial products using computational verb theory was a webcam card counter.
• In 2005, a CCTV flame detector used computational verb theory to make very robust camera fire detection.
• In 2005, a visual automatic driver qualify test system used computational verb theory to make very accurate tracking of vehicles.
• In 2006, Computational verb fuzzy controllers were addressed in the following textbook as a full chapter.


• In 2006, a pornographic image/video filtering software used physical linguistics to model pornographic features in images.

• In 2006, a cognitive image search engine used physical linguistics to understand the images and make the index of massive image database based on image features possible.

• In 2006, Computational verbs are used to program a cognitive stock market chart technical analysis softwear. .

• In 2006, the webcam card counting system was implemented in
an embedded system that uses computational verb theory to enhance the accuracy and
robustness of card counting.
• In 2007, Beijing D.S.Y Technology Co., Ltd developed a CCTV based system for ITS by using computational verb image processing.
• In 2007, the first textbook of physical linguistics entitled: "The Mathematical Principles of Natural Languages: The First Course in Physical Linguistics", was published. Happy 10th birthday!
• In 2007-2008, the first generation of CCTV camera flame detector passed Chinese regulations from Chinese authorities.
• During 2007-2008, the first generation of Chinese young students in Xiamen University had been systematically trained by Professor Tao Yang using the textbook "The Mathematical Principles of Natural Languages".
• In 2008, computational verb theory was applied to control an auto-focusing microscope in IC industry by a third party [download Chinese PDF file].
• During 2008-2009, the second generation of Chinese young students in Xiamen University had been systematically trained by Professor Tao Yang using the textbook "The Mathematical Principles of Natural Languages". We grow fast! (June 5, 2009. Haiyuen 302) [click here to see projects]
• More to come, be prepared...
• Someone used computational verb logic to register a domain name.
| List of Papers and Publications of Computational Verb Theory from Researchers outside YangSky |
|---|
| Jian Zhang and Minrui Fei, Determination of Verb Similarity in Computational Verb Theory, International Journal of Computational Cognition, vol.3, no.3, September 2005, pages 75-78. |
| 朱晟;王中杰;刘勇;夏宝亮, 一种计算动词PID控制器设计的改进, 《系统仿真技术》, 2006年01期. (cached) (pdf) |
| Wanmi Chen and Yanqin Wei and Minrui Fei and Huosheng Hu, "Applications of computational verbs to image processing of RoboCup small-size robots, in Intelligent Control and Automation, Lecture Notes in Control and Information Sciences, vol. 344/2006, pp.494-499, Berlin / Heidelberg, Springer, 2006.(pdf) Abstract: Computational verbs have been applied to digital image processing recently in which the grey values of an image are treated as a dynamic evolving process in space [5]. The paper is to apply such a theory in the RoboCup domain. First, the computational verbs for our small-size soccer robots are developed based on the theory. Then, the modelling and matching are investigated and analyzed to obtain verb similarity. The developed system reduces the computation cost by using row-wise and column-wise compositions of spatial verbs, and makes the vision system have high accuracy and high process speed. |
| 2007西门子杯全国大学生过程控制技能挑战赛12号参赛方案(cached)(pdf) |
| 全程动态视觉交通信息采集分析系统(cached) |
| Yi Guo, A Study of Adverbs as Modifiers of Computational Verbs, International Journal of Computational Cognition, vol.6, no.1, March 2008, pages 31-35. |
| 李静, 计算动词PID控制器在直线电机控制中的应用研究(Research and Application of Computational Verb PID Controller of Linear Motor), 昆明理工大学, 中国优秀硕士学位论文全文数据库, CNKI:CDMD:2.2008.112334 [abstract] [pdf] |
| 于秋水, 安志勇, 王文晶, 李晓静, 刘劲, 张明达, "基于计算动词理论的足球机器人色标设计", 中国仪器仪表学会第九届青年学术会议, 2007年. Abstract: 机器人足球比赛的关键环节是视觉系统,而比赛过程中有关环境的所有信息都是通过视觉系统对色标的识别来获取的,因此足球机器人的色标设计在机器人足球比赛过程中至关重要。计算动词理论是人工智能领域的一项新兴理论,它不仅弥补了静态图像处理过程中的不足,还减轻了图像处理的计算负担。根据计算动词理论处理图像的特点设计一种抗干扰性较强的色标设计方案,利用计算动词理论对该色标设计方案进行识别,能够提高系统辨识精度,简化算法以提高识别速度,满足比赛的实时性。实验表明,该设计方案提高了视觉系统的稳定性和准确性,减少了赛前的准备时间,在比赛中获得了较好的效果,具有良好的应用前景。 |
| 于秋水, 足球机器人视觉信息处理, 2005. Master Thesis [pdf] |
| 中国科学院沈阳自动化研究所[cached Oct. 01, 2009] |
| 朱磊, "机器人三维足球仿真比赛中多智能体及建模方法的研究(Research of MAS and Modeling Methods in RoboCup3D Simulation)", 上海大学.机电工程与自动化学院.控制理论与控制工程.
Master Thesis [cached Oct. 01, 2009] Abstract: RoboCup(Robot World Cup)即机器人世界杯足球锦标赛,是一种典型的多智能体系统。它融合了多个领域的技术,已经成为研究多智能系统的一个标准实验平台。在实际比赛中,需要结合多种技术:如Agent的设计理论、多Agent协作、策略获取、实时推理等。通过具有普遍意义的试验平台,可以深入研究和评价多智能体系统中的各种理论和算法,并将结果推广到众多领域。 本文的主要研究工作和特色是围绕RoboCup3D多智能体体系结构及其核心模块建模展开,内容如下: 1)研究RoboCup3D仿真平台的内部模型和运行机制。以RoboCup3D仿真环境为基础,以智能模型作为智能体系统的软件开发模型,运用模块化设计思想,建立了RoboCup3D仿真智能体体系结构。 2)针对RoboCup3D仿真环境建立世界模型。首先研究了基于卡尔曼滤波的智能体自定位系统,以此为基础建立了智能体的运动子模型、球的运动子模型和智能体的踢球子模型。同时提出了智能体世界模型预测算法。 3)采用数值计算方法建立RoboCup3D仿真队伍的直接射门模型。提出用A*搜索算法建立射门路径寻优,针对A*搜索进行效率优化,减少入队出队的内存分配操作。另外用一数组来记录节点位置,并据此来还原数据,能达到快速建立射门路径的目的。 4)针对不同水平的球队,研究了对手建模。提出了基于计算动词理论的RoboCup3D仿真足球机器人对手建模方法。通过动词理论中模糊扩展的方法建立了计算动词控制器,得出对手控球能力的强弱程度模型,从而实现了在线实时对对手进行能力评估。在以上研究的基础上,本文用面向对象的方法设计了一支仿真球队,并在全国RoboCup比赛中得到验证。 The Robot World Cup ( RoboCup ) is a typical MAS ( Multi-agent System ) in which multi-field technology has been involved and RoboCup has been a standard test platform to study MAS. Many theories are necessary to build a RoboCup team, including agent designing theory, multi-agent cooperation, strategy obtaining, real-time reasoning and so on. Based on this general test platform, various theories of MAS can be researched and applied to many fields. The main research and feature of this paper are as follows. 1) The internal model and function mechanism of RoboCup3D simulation server has been studied in this paper. On the basis of knowledge of RoboCup3D simulation environment, we establish RoboCup3D multi-agent system by using agent model as the software-developing model and adopting modularized designing ideas. 2) The world model is established in RoboCup3D environment. The agent self location system based on Kalman filtering is researched first and it is the basis of studying the movement submodel of agent, the movement submodel of ball, and the kick submodel of agent. The forecasting arithmetic of world model has been presented. 3) Using numerical calculation method for direct-shoot model and putting forward A* search arithmetic to search shooting path while establishing the shoot model of RoboCup3D simulated team. To improve the efficiency of A* search in shoot model, we reduce the manipulation for memory allocation when entering or exiting queue, and use an array to record the node which can be used to rebuild the path. 4) Opponent modeling is studied to adopt rivals at different levels. Based on Computational Verb Theory, an opponent modeling method for RoboCup has been presented. Fuzzy generalization is used to design the computational verb controller, by which the model of extent of opponent’s controlling ability can be obtained to estimate opponent on-line. Based on the above research, a RoboCup3D simulation team is designed with OOP method and this team has been validated in the competition of China RoboCup . |
| 1.
Formation of vertical dislocation patterns in one-dimensional computational verb cellular networksXiaoli Lin; Tao Yang;
Anti-counterfeiting, Security, and Identification in Communication, 2009. ASID 2009. 3rd International Conference on
20-22 Aug. 2009 Page(s):425 - 428
Digital Object Identifier 10.1109/ICASID.2009.5276964
2. Colour tag design of robot soccer based on computational verb theoryQiushui Yu; Zhiyong An; Ruining Yang; Shuang Liang; Electronic Measurement & Instruments, 2009. ICEMI '09. 9th International Conference on 16-19 Aug. 2009 Page(s):4-433 - 4-437 Digital Object Identifier 10.1109/ICEMI.2009.5274042 3. Controlling fuel annealer using computational verb PID controllersYilong Liang; Tao Yang; Anti-counterfeiting, Security, and Identification in Communication, 2009. ASID 2009. 3rd International Conference on 20-22 Aug. 2009 Page(s):417 - 420 Digital Object Identifier 10.1109/ICASID.2009.5276962 4. Collision resolving modeling based on Computational Verb TheoryYinghao Liao; Yi Guo; Tao Yang; Anti-counterfeiting, Security, and Identification in Communication, 2009. ASID 2009. 3rd International Conference on 20-22 Aug. 2009 Page(s):290 - 293 Digital Object Identifier 10.1109/ICASID.2009.5276900 5. Auto-focusing system for microscope based on computational verb controllersWeibin Tang; Yinghao Liao; Zhicong Chen; Lihuan Cai; Tao Yang; Donghui Guo; Anti-counterfeiting, Security and Identification, 2008. ASID 2008. 2nd International Conference on 20-23 Aug. 2008 Page(s):84 - 87 Digital Object Identifier 10.1109/IWASID.2008.4688356 6. A method to derive the probabilities of computational verb events Yi Guo; Tao Yang; Anti-counterfeiting, Security, and Identification in Communication, 2009. ASID 2009. 3rd International Conference on 20-22 Aug. 2009 Page(s):453 - 456 Digital Object Identifier 10.1109/ICASID.2009.5276974 |
|
小型足球机器人系统的实时控制及决策规划研究与实验(pdf) 陈万米 【摘要】: 多机器人系统是在多学科综合的基础上得到发展,涉及到计算机、通信、控制、智能机器人、多传感器及信息融合、视觉及图像处理、人工智能和仿生等相关学科。目前研究多机器人系统的单位与学者在逐年增加,多机器人系统研究水平和研究领域也在不断发展。 本文构建了以小型足球机器人系统为对象的多机器人系统研究平台,并在此平台上进行了理论研究、仿真验证及比赛实践,主要取得了以下创新性的研究成果: 1.提出了计算动词理论结合区域搜索方法解决小型足球机器人系统的实时图像信息获取问题,对机器人标识进行模板匹配和相似度的求解,将计算动词分解为行动词和列动词减轻系统的计算量,尤其研究了光照不均匀情况下难以识别的问题,提高了图像信息的准确性、稳定性,为路径规划等研究打下了基础。 2.将卡尔曼滤波与人工神经网络理论用于小型足球机器人与球的位置预测,可以避开复杂的小型足球机器人建模过程,通过预先采集的输入、输出数据,预测出小型足球机器人的运动轨迹,为小型足球机器人的路径规划和系统决策提供了重要的支撑。 3.在对小型足球机器人进行基本运动轨迹规划的基础上,提出了以Delaunay三角形网格理论指导的优化路径规划,用关键点及其姿态简化对路径的优化思想,使小型足球机器人运动规划能快速找到较优化的路径。 4.提出了将蒙特卡洛理论应用于小型足球机器人系统上,实现系统的增强学习功能,包括个体能力学习和总体策略学习功能,实现了多个小型足球机器人的动态角色分配,避免了运行时的相互冲突,取得了良好配合的效果。 5.研究并运用多传感器和数据融合理论,综合解决了小型足球机器人系统中遇到的小型足球机器人运动的直线校正、运动避障、运动正确性判断、“受伤球员”的智能判断等许多实际问题。 以上研究成果已应用在上海大学小型足球机器人系统上,进行了实验室试验,并在国际国内RoboCup机器人足球赛事上,取得了2004--2007年 RoboCup中国赛连续进入4强以及2007、2008年蝉联伊朗机器人(国际)公开赛冠军的成绩。 Abstract: The development of collaborative multi.robot systems iS multi—disciplinary,involving computer science,communication,control theory,intelligent robots,multi—sensor technology,information fusion, computer vision,bionics,artificial intelligence,etc.Today,the number of scholars and researchers who study collaborative multi.robot systems iS increasing rapidly.The research level and scope of collaborative multi-robot systems are also continuously increasing. In this thesis,small.size robot soccer competition has been as a research platform to conduct the fundamental research.simulation vefificmion and practice competition of a collaborative multi.robot system. The major contributions of the thesis include: 1.The computation verb theory iS combined with the region reconnaissance method to solve the difficulty associated with real.time image acquisition in the small—size soccer robot system.Through matching robot marks,resolving similarity,and decomposing computation verb into a‘low verb’and a‘column verb’.the real.time system computation,as well as the accuracy and stability of image information acquisition under the non.unifoITn illumination condition are greatly improved,laid a solid foundation for path planning research. 2.Based on the study of motion traj ectory of small size soccer competition, the Delaunay triangle grid is used to optimise path scheduling.The key points and their simplified postures are adopted to optimize the robot path SO that the small—size robots are able to plan their paths with a high degree of system stability and fast speeds. 3.The Extended Kalman.Bucy Filter and the RPF neural network are used in small-size soccer robots and their position prediction SO that the complexity of modelling small size soccer robots is greatly reduced. Through the pre-collected input and output data,motion trajectories of small size soccer robots are predicted.This provides an important foundation of path planning and system decision of small size soccer robots. 4.The Monte-Carlo theory is applied to the small-size robot soccer system to study its reinforcement learning,including the overall strategy learning and the individual ability learning.As a result,it has realized many small soccer robot dynamic role assignments,avoided the movement mumal conflict,and obtained the good coordinate effect. 5.Data fusion theory is investigated to solve many practical problems, such as The straight line adjusts,the movement evades bonds,the movement accuracy judgment,the intelligent judgment of“injured player'’in the multi-robot system comprehensively based on the foundation of the multi.sensor system. The research results in this thesis have applied to the small.size robot system of Shanghai University,including many laboratory experiments, participations of many domestic and international robot.soccer competitions.The team continuous entered top 4 in 2004.2007 RoboCup China,became the league champion in 2007 RoboCup Iran Open,as well as the league champion in 2008 RoboCup Iran Open. Keywords: Small—size soccer robot Systems,Extended Kalman-Bucy Filter, Computational verb theory,Reinforcement study,Strategies planning |
| 基于动词控制的自动发电控制(AGC)研究 (pdf) 朱晟 动词控制是智能控制中的一类,它是应用动词集合理论,以动词语言变量和动词逻辑推理为基础的一种计算机数字控制的方法,提供一种实现基于知识规则的,甚至是语言描述的控制规律的机理。动词控制的基本原理是在专家经验和相关领域知识的基础上,总结出若干条以IF条件THEN作用形式表示的动词控制规则,构成描述具有不确定性复杂对象的动词关系,通过被控对象的输出误差和误差变化以及动词关系的推理,合成获得控制量,从而对系统进行控制。 本文研究的是电力系统中的自动发电控制AutomaticGenerationControl,简称AGC。常规的自动发电控制AGC是一个比例积分PI控制调节过程,即根据控制系统的频率和区域净交换功率或两者之一与目标的差值构成区域控制误差AreaControlError—ACE后,按比例积分式计算进行控制。针对传统控制方式中的不足,本文从经典的自动发电控制理论出发,在传统的比例积分PI控制基础上,引入智能控制中的动词控制,实现自动发电控制中二次调节控制,利用动词控制来实现传统的比例积分控制,即动词PI控制,实现控制结构的改进,提高了控制结果的动态性能。 ABSTRACT: Computational verb theory is a kind of computer digital control which is based on the verb set theory,the verb variant and the verb logical inference.It is a realization which is based on the knowledge,even the controlling rules described by language.The basic principal of computational verb control is similar to the fuzzy logic.According to the expert experience and the correlative knowledge,a few IF......THEN verb rules are proposed and make up of the description of the verb relation which has uncertain complex obj ect,and the optimized control parameters are computed by the inference of the verb rules,and then the system is well controlled. Automatic Generation Control(AGC)in power system is discussed in this paper. Conventional AGC is a procedure which is aproportional integral(PI)contr01.That is to say,Area Control Error(ACE)is controlled which is followed by PI control and ACE is defined as a linear combination of system frequency error and the sum of errors of interchange of power between diferent areas or either of them.After studying the classic theory of AGC,the deficiency of conventional AGC control model is analyzed and this paper introduces V-erb control of intelligent control into PI control to formulate Vrerb PI contr01.And then it is used in the second adjustment of the AGC.The control structure of AGC is improved and the dynamics of control results become beter. Key Words:verb control,intelligent control,PI controller,automatic generation control,area control error |
| 计算动词理论及应用研究(Research on Computational Verb Theory and Its Applications)(pdf) (pptA)(pptB) 郭奕 摘要: 自然语言是人类发明的最为综合、最具柔性、自适应极强的建模物理世界和 意识世界的工具,使其可测量化一直都是人们不断努力的目标。计算动词理论正 是为了实现这个目标而诞生的。作为一门新兴的学科,计算动词理论已经渗透到 了自动控制、人工智能等成熟的领域。此外,计算动词理论也成功地应用于各种 工业系统,如视频火灾检测系统、智能交通系统、智能安防系统等等。因此,计 算动词理论具有很高的研究价值。 本文从计算动词事件、计算动词神经网络和计算动词PID控制器这三个方面 对计算动词理论进行了探索和研究。这不但能够利用现有的成果推动计算动词 理论的发展,还可以在一定程度上丰富概率论、人工神经网络和PID控制技术。 本文提出了一种计算动词事件概率的测量方法,完成了I型通用计算动词神经网 络的设计和学习算法的推导,并详细给出了三种第二代计算动词PID控制器的设 计。 本文的创新点主要体现在以下几个方面: 1. 第一次引入了计算动词观察函数的概念,这使计算动词事件的建模和概率 测量更加灵活、便捷; 2. 提出的计算动词神经网络可以用于包含多条规则的计算动词规则库的学 习; 3. 设计了两种基于趋势相似度的计算动词PID控制器; 4. 第一次全面地研究了各种计算动词PID控制器的信号跟踪新能。 关键词: 计算动词理论概率人工神经网络PID控制器 Abstract: Natural languages are invented by human beings for general-purpose commu- nication, moreover, are the most comprehensive, °exible and adaptive tools for modeling the physical and the cognitive world. Scientists and scholars have been striving for making them measurable for years. Computational verb theory (CVT) is a new paradigm of making natural languages measurable. As an emerging dis- cipline, CVT has been applied in well-established ¯elds such as automatic control and arti¯cial intelligence and etc. Moreover, it has been utilized by many indus- trial systems, for instance, visual °ame-detecting, intelligent tra±c system and intelligent security system. Therefore, it's worthwhile to make an intensive study of CVT. In this thesis, CVT is studied from three aspects; namely, computational verb events, computational verb neural networks and computational verb PID con- trollers, which not only promotes CVT's development by taking the advantage of existing results but also adds new dimensions to probability theory, arti¯cial neu- ral networks and the PID controllers to some extent. This thesis proposes a new method of deriving the probability of computational verb events, gives the struc- ture of type-I generalized computational verb neural network and the derivation of its learning algorithm, studies three types of the second-generation computational verb PID controllers in details. The innovations of the thesis are listed as follows. 1. For the ¯rst time, it introduces the concept of computational verb observation function , which makes the modeling of computational verb events and the measurement of probabilities more °exible and convenient; 2. The proposed computational verb neural networks are suitable for learning mul- tiple verb rules; 3. Two types of computational verb PID controllers based on trend-based compu- tational verb similarities are designed; 4. It is the ¯rst comprehensive study on the signal tracking performance of com- putational verb PID controllers. Keywords: computational verb theory; probability; arti¯cial neural network; PID controller |
| 芯片显微自动拍照技术及其系统设计研究(Research and Design of Microscopic IC Photo Auto-taking System)(doc)(ppt) 汤伟宾 摘 要: 科技的发展,使芯片大大改善了我们的工作效率以及生活起居等。芯片反向工程作为借鉴国内外先进的芯片设计技术的一种方式而备受关注,而芯片显微拍照和图像拼接工作是芯片反向工程顺利进行的前提。随着芯片集成度的提高,采用自动化的方式,提高反向工程的效率,已成必然趋势。本文的工作就是搭建芯片显微自动拍照系统,解决自动聚焦、运动控制、图像拼接等问题,以提高反向设计的效率,实现芯片显微拍照的自动化。 本论文首先介绍了自动聚焦技术的基本原理,并在分析对比传统的自动聚焦算法的基础上,提出一个具有普遍意义的自动聚焦优化算子,以满足各种不同场合的聚焦需求;其次根据先进的计算动词理论,设计了一套计算动词控制规律以及相应的控制器模型修正算法,大大提高了自动拍照系统的控制效率以及鲁棒性;接着阐述了图像拼接、图像融合的基本原理;然后按照模块划分的方式,说明了整个芯片显微自动拍照系统的具体设计方案,提出了基于阈值的图像误匹配点去除方法;最后给出了整个系统的操作说明书、实例测试以及相应的实验数据,说明本设计的有效性。 本论文的特色与创新点主要体现在以下几个方面: 1) 根据自动聚焦算法的共同特征,提出了一个具有普遍优化意义的自动聚焦优化算子,解决图像清晰度判断的问题,在增加少许计算量的情况下,改善各种传统自动聚焦算法的灵敏度。 2) 采用先进的计算动词理论,设计了一套自适应的控制规律,解决自动聚焦控制算法问题,大大提高了整个自动拍照系统的控制效率,以及系统的鲁棒性。 3) 根据自动聚焦基本模型,设计了控制器模型修正算法,解决外界环境因素的影响,使系统具有自学习能力,进一步提高了拍照系统的鲁棒性。 4) 根据匹配点分布情况,提出了一个基于阈值的误匹配点去除算法,提高了图像拼接融合的准确性,解决匹配点误判问题。 关键词:自动聚焦;计算动词;图像拼接; ABSTRACT: As the development of Science Technology, chips have been playing an important role in our life and work. IC Reverse Engineering, a way to study advanced IC designing technology, has been especially concerned. Taking IC layout images under microscope and image matching ensure the success of IC Reverse Engineering. As the expansion of chip size, it is necessary to reverse automatically to improve its efficiency. Our work is to design such a system, Microscopic IC Photo Auto-taking System. It solves such problems as carema auto-focusing, motion controlling, image matching and so on, for IC Reverse Engineering. Thus, it improves its efficiency dramatically. In this paper, we firstly introduce the basic principle of auto-focusing. After analyzing the traditional auto-focusing algorithms, we put forward an optimizing operator for all auto-focusing algorithms, to meet different kinds of requirement. Secondly, we design a set of computational verb rules based on computational verb theory, and we call it verb controller. We also design a model amending algorithm for this controller. All these improve the system's working efficiency and robustness. Thirdly, we explain the principle of image matching and image fusion, and design an algorithm based on threshold to remove the mismatching-points during image matching. After these, we propose the whole design proposal for our system, and divide it into modules. Finally, we show the manual of our system, testing examples and its performance. The characteristics and innovations of the platform designed in this thesis are as follows: 1) In order to judge whether an image is clear or not, we propose an optimizing operator for all auto-focusing algorithms. This operator improves the performance of different auto-focusing algorithms obviously, without increasing the computation time. 2) Based on computational verb theory, we design a verb controller made up of a set of computational verb rules, for stepper motor to control the process of auto-focusing. It cuts down the time spent on auto-focusing dramatically. It can also enhance the system robustness. 3) According to the basic model of auto-focusing, we design a model amending algorithm for this controller. it not only makes the verb controller independent of environment, but also ensures the ability of self-learning and self-adaptive for our system. 4) According to the distribution of image matching points, we bring foward a mismatching-pionts removing algorithm based on threshold, to solve the mismatching problem of the image matching algorithms. It makes our system more accurate. Key Words: Auto-focusing; Computational Verb; Image Matching |


