King Ngi 顔慶義 (IEEE & IET Fellow)
The Chinese University of Hong Kong, Hong Kong
received his B.Sc. (Hons) and Ph.D. degrees, both in Electrical
Engineering from Loughborough University, U.K., in 1978 and
1982, respectively. He joined the Department of Electronic
Engineering, the Chinese University of Hong Kong as Chair
Professor in 2003. He has been appointed
Chair Professor at the University of Electronic Science and
Technology, Chengdu, China, under the National Thousand Talents
Program (千人计划) since 2012. Previously he was a Full Professor at
the School of Computer Engineering, Nanyang Technological
University, Singapore, and the School of Electrical, Electronic
and Computer Engineering, University of Western Australia,
Australia. He was appointed as Honorary Professor of Tunku Abdul
Rahman University in Malaysia, Adjunct/Visiting Professor of
Zhejiang University, Shanghai Jiaotong University, Shanghai
University, Huazhong University of Science and Technology and
Huaqiao University in China, Distinguished Adjunct Professor of
the National Sun Yat-sen University in Taiwan, and Adjunct
Professor of the University of Western Australia and RMIT
University in Australia. He served as the External Examiner for
the B.Eng. degree program of Malaysia's Multimedia University,
and was appointed as IEEE Distinguished Lecturer of the IEEE
Circuits and Systems Society in 2006-2007.
Prof. Ngan is active in many professional activities. He was an associate editor of the Journal on Visual Communications and Image Representation, U.S.A., and an area editor of EURASIP Journal of Image Communications, and served as an associate editor of IEEE Transactions on Circuits and Systems for Video Technology and Journal of Applied Signal Processing. He chaired a number of prestigious international conferences on video signal processing and communications and served on the advisory and technical committees of numerous professional organizations. He co-chaired the IEEE International Conference on Image Processing (ICIP) in 2010 in Hong Kong. He has published extensively including 3 authored books, 6 edited volumes and over 300 refereed technical papers in the areas of visual signal processing, image/video coding and multimedia communications, which are his main research interests. He also holds 11 patents on image coding/transmission techniques. (Full CV)
Title: 3D Morphable Model and its Applications
Speech Abstract: In this talk, the research work on 3D morphable model and its applications conducted in the Image and Visual Processing (IVP) Laboratory of the Chinese University of Hong Kong (CUHK) is discussed. The 3D morphable model is introduced with respect to the works carried out for face modeling and reconstruction. Its applications to head pose tracking, facial expression tracking, and face reconstruction using a single color image are explored. Demonstrations showing the results obtained are displayed in video. Lastly some future directions will be outlined.
Prof. Changhuei Yang (Coulter
Fellow, AIMBE Fellow, OSA Fellow, and SPIE Fellow)
California Institute of Technology, USA
PhD, EECS, MIT, 2002; BSc, Mathematics, MIT, 2002; MEng, EECS, MIT, 1997; BSc, Physics, MIT, 1997; BSc, EECS, MIT, 1997
Field of Study
Professor Yang's research efforts are in the areas of novel microscopy development and time-reversal based optical focusing. Prof. Yang joined the California Institute of Technology in 2003. He is a professor in the areas of Electrical Engineering, Bioengineering and Medical Engineering. He has received the NSF Career Award, the Coulter Foundation Early Career Phase I and II Awards, and the NIH Director's New Innovator Award. In 2008 he was named one of Discover Magazine’s ‘20 Best Brains Under 40’. He is a Coulter Fellow, an AIMBE Fellow and an OSA Fellow.
His research efforts can be categorized into two major groups:
High-throughput microscopy - Prof. Yang's group is developing a number of technologies aimed at transforming the conventional microscope into high throughput, automated and cost-effective formats. His group is the pioneer of the first chip-scale microscope system - the optofluidic microscope. The ePetri system was also invented by his group and it represents a cost-effective and highly autonomous way of performing high-content microscopy imaging. His group’s recent invention - Fourier Ptychography, is a computational microscopy method that enables a standard microscope to push past its physical optical limitations to provide gigapixel imaging ability.
Time-reversal based optical focusing and imaging - Prof. Yang's group is working on the use of 'time-reversal' techniques to undo the effect of tissue light scattering. This work has the potential to enable greatly improved depth-penetration and resolution improvement for deep tissue optical imaging. It also opens up the possibility for performing incision-less laser surgery and precision cancer therapy.
Speech Title: Fourier Ptychography – Using computation to address physical optical challenges
Speech Abstract: Microscopes are complex and fussy creatures that are capable of delivering limited image information. This is because physical optical lenses are intrinsically imperfect. Building better microscope has traditionally focused on using ever more complicated optical element arrangements to minimize aberrations. I will discuss our recent work on Fourier Ptychographic Microscopy - a computational microscopy method that shifts the challenge of addressing aberrations from the physical world to the computational realm where aberrations become readily solvable mathematical problems. In the process, we enable a standard microscope to push past its physical optical limitations to provide digital refocusing, improved spatial-bandwidth product and phase imaging capabilities.
Nanyang Technological University, Singapore
Prof. Xudong Jiang received the B.Sc. and M.Sc. degree from the University of Electronic Science and Technology of China, in 1983 and 1986, respectively, and received the Ph.D. degree from Helmut Schmidt University Hamburg, Germany in 1997, all in electrical and electronic engineering. From 1986 to 1993, he worked as Lecturer at the University of Electronic Science and Technology of China where he received two Science and Technology Awards from the Ministry for Electronic Industry of China. He was a recipient of the German Konrad-Adenauer Foundation young scientist scholarship. From 1993 to 1997, he was with Helmut Schmidt University Hamburg, Germany as scientific assistant. From 1998 to 2004, He worked with the Institute for Infocomm Research, A*Star, Singapore, as Senior Research Fellow, Lead Scientist and appointed as the Head of Biometrics Laboratory where he developed a fingerprint verification algorithm that achieved the fastest and the second most accurate fingerprint verification in the International Fingerprint Verification Competition (FVC2000). He joined Nanyang Technological University, Singapore as a faculty member in 2004 and served as the Director of the Centre for Information Security from 2005 to 2011. Currently, Dr Jiang is a tenured Associate Professor in School of Electrical and Electronic Engineering, Nanyang Technological University. Dr Jiang has published over hundred research papers in international refereed journals and conferences, some of which are well cited on Web of Science. He is also an inventor of 7 patents (3 US patents), some of which were commercialized. Dr Jiang is a senior member of IEEE and has been serving as Editorial Board Member,Guest Editor and Reviewer of multiple international journals, and serving as Program Committee Chair, Keynote Speaker and Session Chair of multiple international conferences. His research interest includes pattern recognition, computer vision, machine learning, image analysis, signal/image processing, machine learning and biometrics.
Title: Iterative Truncated Arithmetic Mean Filter
and Its Properties
Speech Abstract: The arithmetic mean and the order statistical median are two fundamental operations in image processing. They have their own merits and limitations in noise attenuation and image structure preservation. Comparing with the arithmetic operation, data sorting required by the median-based filters is a complex process and is intractable for multivariate data. This talk explores the relation between the two very often used fundamental statistics, namely, the arithmetic mean and the order statistical median. It unveils some simple statistics of a finite data set as the upper bounds of the deviation of the median from the mean. It is desirable to develop a filter having the merits of both the types of filters. The proposed Iterative Truncated arithmetic Mean filter, ITM filter, circumvents the data-sorting process but outputs a result approaching the median. Proper termination of the proposed ITM algorithm enables the filters to own merits of the both mean and median filters and, hence, to outperform both the filters in many image processing applications.
Prof. Chin-Chen Chang
IEEE and IET Fellow, Feng Chia University, Taiwan
Chin-Chen Chang obtained his Ph.D. degree in computer
engineering from National Chiao Tung University. His first
degree is Bachelor of Science in Applied Mathematics and master
degree is Master of Science in computer and decision sciences.
Both were awarded in National Tsing Hua University. Dr. Chang
served in National Chung Cheng University from 1989 to 2005. His
current title is Chair Professor in Department of Information
Engineering and Computer Science, Feng Chia University, from
Prior to joining Feng Chia University, Professor Chang was an associate professor in Chiao Tung University, professor in National Chung Hsing University, chair professor in National Chung Cheng University. He had also been Visiting Researcher and Visiting Scientist to Tokyo University and Kyoto University, Japan. During his service in Chung Cheng, Professor Chang served as Chairman of the Institute of Computer Science and Information Engineering, Dean of College of Engineering, Provost and then Acting President of Chung Cheng University and Director of Advisory Office in Ministry of Education, Taiwan.
Professor Chang's specialties include, but not limited to, data engineering, database systems, computer cryptography and information security. A researcher of acclaimed and distinguished services and contributions to his country and advancing human knowledge in the field of information science, Professor Chang has won many research awards and honorary positions by and in prestigious organizations both nationally and internationally. He is currently a Fellow of IEEE and a Fellow of IEE, UK. And since his early years of career development, he consecutively won Institute of Information & Computing Machinery Medal of Honor, Outstanding Youth Award of Taiwan, Outstanding Talent in Information Sciences of Taiwan, AceR Dragon Award of the Ten Most Outstanding Talents, Outstanding Scholar Award of Taiwan, Outstanding Engineering Professor Award of Taiwan, Chung-Shan Academic Publication Awards, Distinguished Research Awards of National Science Council of Taiwan, Outstanding Scholarly Contribution Award of the International Institute for Advanced Studies in Systems Research and Cybernetics, Top Fifteen Scholars in Systems and Software Engineering of the Journal of Systems and Software, Top Cited Paper Award of Pattern Recognition Letters, and so on. On numerous occasions, he was invited to serve as Visiting Professor, Chair Professor, Honorary Professor, Honorary Director, Honorary Chairman, Distinguished Alumnus, Distinguished Researcher, Research Fellow by universities and research institutes. He also published over hundreds papers in Information Sciences. In the meantime, he participates actively in international academic organizations and performs advisory work to government agencies and academic organizations.
Title: A Self-Reference Watermarking Scheme based
on Wet Paper Coding
Speech Abstract: Fragile watermarking is applied to protect the integrity of the digital media. Current fragile watermarking schemes mainly provide the functionality of detecting and locating the tampered regions of an authorized image. The capability to recover the tampered regions has rarely been discussed in the literature. In fact, the recovery ability is an important issue while proving and maintaining the image integrity. For achieving these purposes, we first utilize the concept of self-reference to preserve the significant information of a protected image. Then we embed the information into the protected image using the technique of wet paper coding. According to experimental results, the new scheme is highly sensitive to detect and locate the tampered area. In particular, the results show that the quality of recovery image is satisfactory.
Kingston University, United Kingdom
Jamshid Dehmeshki is a full-time Professor of Medical Image Analysis in the Faculty of science, engineering and computing at Kingston University, UK, where he is a director of a recent established laboratory/Center, QMIC (Quantitative Medical Imaging lab/Centre). QMIC is collaboration between Kingston University (KU) and the University Hospital of Lausanne (CHUV). The primary purpose of QMIL is to research and develop novel medical image analysis algorithms and software and to validate their effectiveness in a clinical environment. In this capacity, he is also the Founder of Mediar (www.mediar.co.uk) - a sole trader company involves in developing state-of-the-art medical image and data analysis software. He is currently main supervisor (director of study) of thirteen Postgraduate students. He has published more than 140 scientific research papers, five book chapters, and holds thirteen patents.
His long-term research focuses on computer-aided detection (CAD) and Measurement (CAM) of lesions in medical images. CAD research aims at discovering the fundamental perception processes of human vision in the image-based diagnosis of lesions, and developing mathematical/computational models that describes them. His most recent research has concentrated on detecting, measuring and quantifying the vascular diseases using CT angiography.
In addition to research activities, He has got depth knowledge of product development life cycle. Over last five years of working at Mediar, He designed the detailed architecture of several image processing libraries for direct integration into third party products/workstations and a variety of image processing algorithms to build a robust general image processing library for rapid product development. he has also developed a series of functionality for image analysis including a family of CAD and CAM libraries to automatically detect quantify and characterise a region of interest within human body. In addition to IP library, he has developed a medical imaging platform with sophisticated GUI using .NET and WPF. The platform were used to integrate all CAD system technology.
Over five years of working at Medicsight Plc as CTO (2001-2006), he was instrumental in the designing and development of three families of state-of-the-art medical imaging software products, namely, Colon CAR (Computer Assisted Reader), Heart Screen and Lung CAR, which received FDA approval and CE marking. He led the delivery of five major medical software products with FDA approval and CE marking. He designed and patented the architecture for image processing products with features that achieved FDA 510(K) compliance.
Prof. Yan Yang
Southwest Jiaotong University,China
Dr. Yan Yang is
currently Professor and vice dean of Information Science and
Technology, Southwest Jiaotong University. She worked as a
visiting scholar at the Center of Pattern Analysis and Machine
Intelligence (CPAMI) in Waterloo University of Canada for one
and half year. She is an Academic and Technical Leader Candidate
of Sichuan Province. Prof. Yang has participated in more than 10
high-level projects recently. And have taken charge of two
programs supported by the National Natural Science Foundation of
China (NSFC), one NSFC International (Regional) Cooperation and
Exchanges program, one Project of National Science and
Technology Support Program, and one Supporting Program for
Science and Technology of Sichuan Province. She has authored and
co-authored over 130 papers in journals and international
conference proceedings, 1 special issue of international
journal, 1 proceeding and 2 books. She also serves as the Vice
Chair of ACM Chengdu Chapter, Member of IEEE, Senior Member of
CCF and CAAI, Member of CCF Education Work, Artificial
Intelligence and Pattern Recognition, Theoretical Computer
Science Committee, Member of CAAI Machine Learning, Rough Set
and Soft Computing Committee, Deputy Secretary General of
Sichuan Province Computer Society and Vice Chair of Big Data
Industry University Research Council of Sichuan Institute of
Speech Title: Multi-view Clustering for Big Data
Speech Abstract: Real-world datasets often have representations in multiple views or come from multiple sources. Then multi-view clustering have gradually become hot issues in machine learning research. The traditional clustering algorithms are not yet adapted to the challenges of big data, which is much more complicated than ever before with multi-view characteristics. Exploiting consistent or complementary information from multi-view data, the multi-view clustering aims to get better clustering quality rather than rely on the individual view, especially for image data. The main challenge is how to integrate this information and give a compatible clustering solution across multiple views. In this talk, I will discuss multi-view learning and clustering, and also give several examples of mining big data being conducted in my research group.