Department of Computer Science, Tokyo City University
Title: Hue Preserving Color Image Processing in RGB Color Space
Preserving hue is an important issue for color image processing. In order to preserve hue, color image processing is often carried out in HSI or HSV color space which is converted from RGB color space. Transforming from RGB color space to another color space and processing in this space usually generate the gamut problem. If color image processing with hue preserving is performed in RGB color space, the gamut problem is solved. Two hue preserving techniques, namely, scaling and shifting, for the processing intensity and saturation components in RGB color space are clearly indicated.
In this talk, we introduce some hue preserving methods in RGB color space without gamut problem based on these two concepts. Eventually, we introduce an intensity processing method while preserving hue & saturation and a saturation processing method while preserving hue & intensity. Arbitrary gray-scale transform methods can be applied to both the intensity component and the saturation component. Two processing methods are completely independent. Therefore, two methods are easily combined by applying two processing methods in succession. The combination method realizes the hue-preserving color image processing with a high arbitrariness without gamut problem. Furthermore, the concrete enhancement algorithm by using S-type transformation based on the combination method is introduced.
Akira Taguchi received the B.E., M.E. and Dr. Eng. Degrees in electrical engineering from Keio University, Yokohama, in 1984, 1986, 1989 respectively. In 1989, he joined Musashi Institute Technology (the old name of Tokyo City University). He is currently a Professor at the Department of Computer Science, Tokyo City University. From 1993 to 1994 he spent one year at the Signal Processing Laboratory, Tampere University of Technology, Finland as a visiting Researcher. His research interests are in the areas of digital image processing including nonlinear signal processing and color image processing. He served General Chair for IEEE ISPACS 2013. He is currently a Vice Chair of International Steering Committee of ISPACS. He is a senior member of IEEE and a fellow of IEICE.
Director, Center of Excellence in Community Health Informatics, Chiang Mai University
Title: Digital Disease Detection: a New Approach for Early Warning of Outbreak Using Infodemiology
In many outbreaks, Southeast Asia has somehow become a potential originate area of the pandemic due to the emerging of technology and faster international logistics. Currently, traditional surveillance system has been existed but its report is not up-to-date. Our study aims to advance the digital infectious disease detection by developing an internet-based surveillance of the infodemiological data integrated with the existing traditional surveillance data. The system is extended from DigiHealth application. User can report their illness that occurred to themselves or other family members. User can also report any suspected or abnormal threat to human health from animals or surrounding environment. Data will be sent to DigiHealth server in digital form, together with the device location. Data interpretation are presented in a web-based spatial information that containing a prevalence and incidence of a certain epidemic. Comprising of an ongoing systematic collection, a novel analysis algorithm, and the interpretation module of health data, the developed system is helpful for planning, implementing and evaluating of the contagious disease control. The usability test was performed using ISO 9241-11 standards for the efficacy, effectiveness, and user satisfaction tests. Our developed system is working flawlessly. Data submitting and retrieval process is precise and accurate. However, the accuracy of the epidemic prediction and epidemiological parameterization need a further improvement.
Associate professor Ekkarat Boonchieng obtained his Ph.D. in computer science from Illinois Institute of Technology. His background is also computer science from Khon Kaen University (Bachelor Degree) and University of New Haven (Master Degree). He is a director of Center of Excellence in Community Health Informatics, Chiang Mai University. His research interests are biomedical engineering, medical image processing and big data in health informatics.
Professor, Sirindhorn International Institute of Technology Thammasat University
Title: Gradient orientation information for applications in image processing and computer vision
Gradient orientation (GO) carries significant information in an image. It is well known that GO is robust to varying lighting conditions. This is an important advantage of GO compared with traditional image features, such as intensities and gradients. I learned this strength when I was engaged in research for my 2nd Master’s degree at the University of Sydney from 1995 to 1997. Since then, I have been using GO to various applications in image processing and computer vision. Today I would like to talk about several research topics based on GO, including human face detection and tracking, optical flow estimation, blood vessel detection in retinal images, and digital watermarking.