Title: Recognizing Patterns with Structures: From low-level Features to high-level Human Perspective

Speaker: David Siu-Yeung CHO, BEng(Hons), PhD
School of Computer Engineering, Nanyang Technological University, Rm N4-02a-32, Singapore

Abstract:
Traditional pattern recognition methods focusing on the problem of identifying simple two-dimensional templates do not take into account the human ability to recognize varied and novel patterns. Feature theories ignore evidence that processing of global form often takes priority over processing of local features and are sensitive to context in which the stimulus appears. Pattern recognition systems usually consist of three steps of data acquisition, feature extraction and classification. Feature extraction process in pattern recognition, produces errors, more than often, is due to the operating environment that the feature extractor used. Typically, a recognized object can be subjected to various degrees of changes. This motivates us to develop another kind of feature representations for pattern recognition. Many natural or artificial systems are more appropriately modeled using ¡°Data Structures¡±. By incorporating structures in extracted features, it would facilitate the data processing process and later pattern recognition process. As a result, the recognition systems would be more effective and robust. In this talk, I will present an investigation of the use of connectionist models to generalize structural information, which perform like a human cognition for recognizing erratic patterns. Erratic patterns here mean that incomplete features are extracted by feature extractor in a pattern recognition system, caused by occlusions in the data or un-filterable noise in the pattern. A computational framework for learning a flavor of structural connectionist models is of paramount importance for both pattern recognition and development of brain-inspired systems, since it allows the treatment of structured information very naturally and, in several cases, very efficiently. The details of this framework will be introduced in this talk. Several research issues will be addressed and examined for this framework. Several studies in relating to the application of the potential of connectionist models for pattern recognition were carried out to provide evidence that the connectionist model is able to improve the accuracy of recognition rates of variations presented in the extracted features. Particularly, facial emotion recognition is applied to demonstrate the robustness of the connectionist models for recognizing faces with occlusions, which forms erratic patterns of the features and caused the problems in recognition.

Short Bio:
Dr. CHO Siu Yeung, David is an Assistant Professor in the School of Computer Engineering at Nanyang Technological University (NTU). Concurrently, he is the Director of Forensics and Security Laboratory (ForSe Lab) in the same school. In his tenure of directorship, he involves to create and organize the lab dedicated to research in the application of computational techniques to biometrics and forensics analysis. Prior to joining NTU in 2003, he was a Research Fellow for The Hong Kong Polytechnic University and City University of Hong Kong between 2000-03, where he worked some projects for neural networks and adaptive image processing. He also led a project of content-based image analysis by novel machine learning model, which is one of the projects attached in the Centre for Multimedia Signal Processing at PolyU HK. He is the co-inventor of the neural color reflectance model to tackle the multi-coloured shape from shading problem in which he has published several papers in the premium international journals. Dr. Cho earned his PhD from the City University of Hong Kong in 1999. His research topic was to develop an effective neural network learning algorithms in applying to the 3D shape reconstruction. He has published one monograph book, three book chapters, and over 50 technical papers in which more than 15 papers are in the top-notch international journals (IEEE Trans. Neural Network, IEEE Trans. Knowledge & Data Engineering, Neural Computation, Pattern Recognition,¡¦ etc). Dr. Cho received numerous research grants as a principal investigator, funded by Ministry of Education, Institute for Infocomm Research and NTU. He also received a highly competitive grant from Hong Kong Research Grant Council for fundable research project as a co-investigator in 2003. He is a member of IET and IEEE. Dr. Cho works extensively in the area of computational intelligence, pattern recognition and computer vision. The recent publication indicates the active contributions in the areas of computational intelligences, image analysis, and computer vision. The long-term research plan is to establish a research programme that making use of computational techniques to solve out the real-life problems in different areas, such as, healthcare, education, homeland security and even social sciences. Dr Cho was received twice ROAR (Research Outstanding and Award Recognition) at NTU in 2006 and 2007 respectively. His recent co-authored paper entitled ¡°A Physiological Vein Pattern Biometric System¡± was also shortlisted in the Hong Kong Institute of Engineer Outstanding Paper Award for Young Engineers/Researchers in 2008. Dr. Cho has served as program committees, session chairs, and organizers in many technical sessions at various international conferences.

Title: Pen-based Interactive System and Computer Vision.

Speaker: Jungpil Shin, Ph.D Associate Professor
Multimedia Systems Lab,School of Computer Science and Engineering, The University of Aizu, Japan

Abstract:
We are mainly studying the way to use human handwriting with pen-tablet system. Since we have the knowledge of the writing order of a character using the system, it is easier to analyze the handwriting and to develop various applications. The topics are as follows: On-line stroke-order and Stroke-number free character recognition, Signature verification, Studying the effect of alcohol to signing, Signature evaluation, Kanji (Chinese characters in Japanese) learning System, Handwritten style font generation system (Handwriting synthesis with one's style), Oriental writing brush implementation (3D virtual brush), and 3D Character recognition using Wii controller. Based upon the above researches in handwriting analysis, we are also studying on image retrieval system and material/biomedical image analysis. For the image retrieval system, we are studying on the use of pen-tablet system. By simplifying input process using the system, we are aiming the higher accuracy and faster searching speed. As the study on material/biomedical image analysis, we try to analyze the structure of a mouse¡¯s brain cell using the pattern matching techniques and also to develop an automation program which can detect contact points of two materials precisely in nano-scale.

Short bio.
Jungpil Shin received a BS in Computer Science and Statistics and MS in Computer Science from Pusan National University, Korea in 1990 and 1994, respectively. He received a PhD in Communication Engineering from Kyushu University, Japan in 1999. He became an Assistant Professor and Associate Professor at the Department of Computer Software, the University of Aizu, Japan in 1999 and 2004 respectively. Research interests include Pattern recognition, Character recognition, Image processing, and Computer vision. He is currently researching the following advanced fields: Pen-based interacting system, Real-time system, Oriental character processing, Mobile computing, Computer education, Human recognition, and Machine Intelligence. He is a member of the IEEE Computer Society; Information Processing Society of Japan; Institute of Electronics, Information, and Communication Engineers; and Korea Information Science Society.

Title : ACP based Control & Management for Complex Networked Systems
Speaker : Dr. Fei-Yue Wang

SUMMARY

In this presentation, we will introduce a new mechanism for intelligent control of real-world large and complex networked systems using the concept of parallel control or parallel management based on the ACP approach, that is, modeling with Artificial systems, analysis by Computational experiments, and control through Parallel execution for complex problems. Agent technology and various methods in computational intelligence are critical to the successful applications of parallel control and management. Particularly, we will discuss the use of linguistic dynamic systems (LDS), adaptive dynamic programming (ADP), agent-based control (ABC), data-driven decision-making and machine learning in ACP-based controls and some examples of their real-world applications in transportation, production, and cyber-physic-social systems.

BIO

Fei-Yue Wang received his Ph.D. in Computer and Systems Engineering from Rensselaer Polytechnic Institute, Troy, New York in 1990. He joined the University of Arizona in 1990 and became a Professor and Director of Program in Advanced Research for Complex Systems. In 1999, he found the Intelligent Control and Systems Engineering Center at the Chinese Academy of Sciences, Beijing, China, under the support of the Outstanding Oversea Chinese Talents Program. Since 2002, he is the Director of the Key Laboratory of Complex Systems and Intelligence Science at the Chinese Academy of Sciences. From 2005 to 2009, he was the dean of School of Software Engineering, Xi¡¯an Jiaotong University, China. Currently, he is vice president for research, education, and academic exchange at the Institute of Automation, Chinese Academy of Sciences. He was the Editor-in-Chief of the International Journal of Intelligent Control and Systems from 1995 to 2000, Series in Intelligent Control and Intelligent Automation from 1996 to 2004, IEEE Intelligent Systems from 2009-2010, and IEEE Trans on ITS from 2008-2011. Since 1997, he has served as General or Program Chair of more than 20 IEEE, INFORMS, ACM, ASME international conferences. He was the President of IEEE ITS Society from 2005 to 2007, the President of Chinese Association for Science and Technology (CAST, USA) in 2005, and the President of the American Zhu Kezhen Education Foundation from 2007-2008. Currently, Dr. Wang is a member of ACM Council and WSRI Scientific Council, and Chair of IFAC Technical Committee on Economic and Business Systems. Dr. Wang is member of Sigma Xi and an elected Fellow of IEEE, INCOSE, IFAC, ASME, and AAAS. In 2007, he received the 2nd Class National Prize in Natural Sciences of China and awarded the Outstanding Scientist by ACM for his work in intelligent control and social computing. In 2009, he received IEEE ITSS Outstanding ITS Application Award.

Title : Support Search and Retrieval of Design Patterns through Vocabulary Control
Speaker : Youngsuk Cho, Ph. D.

SUMMARY

In this keynote speech, we will provide an introduction to the principal concepts of Design Patterns, their advantages and drawbacks, and needs to enhance the reusability in terms of the search and retrieval of Design Patterns with a controlled set of vocabulary in Design Catalogs. This may require a limited amount of additional effort. However, regarding the underlying philosophy of Design Patterns, i.e. reusability, search and retrieval activities must be supported. We suggest that a Prolog description of Patterns be included in the Catalog as one of its subsections.

Biography :

Youngsuk Cho received his Ph.D. in Computer Science from Louisiana State University, Baton Rouge, Louisiana, U.S.A. He joined Dongguk University in 1995. He is now a Professor and the Chairman of the Division of Computer Science and Multimedia Engineering. He was with Fujitsu Korea, Ltd. and Louisiana State University as a Systems Analyst and as a Computer Analyst, respectively. He also worked as a Member of Software Engineering Test Committee, Federal Government Employee Recruitment Test Program, the Executive Auditor of Korea Business Incubator Association, and an Executive of Korea Multimedia Society. He was the Program Chair of ICCIT2009. He is the Program Chair of NISS2010 and INC2010. His research areas include Software Reusability, Software Development Methodology, Agile Models, and Design Patterns.