Inaugural Keynote Lecture
Wai Ho Mow
Senior Member, IEEE,
Hong Kong University of Science and Technology, Hong Kong

From Barcoding to Unobtrusive Display-camera Communications
[ 11:30 am, 04-Jun-2018 ]

Nowadays, barcodes have been widely used as a ubiquitous gateway to connect the offline physical world to the online cyber world. For example, QR codes are commonly used in marketing campaigns to enable potential customers to access online advertisement content. However, the conventional barcodes do not have an appealing visual appearance and are not very effective in engaging customers. In this talk, our development of a new picture-embedding barcode, called PiCode, is presented. PiCode is designed with careful considerations on both the perceptual quality of the embedded image and the decoding robustness of the encoded message. Comparing with existing beautified QR codes, PiCode can achieve better perceptual quality for a given embedded image, and maintains a better tradeoff between image quality and decoding robustness in various application scenarios. Our further enhancements of PiCode allow very high quality image and video embedding. These recent developments bring new possibilities to the exciting topic of unobtrusive display-camera communications, which potentially allow billions of existing display and camera devices to communicate without hardware upgrading. The real-world applicability of PiCode and its extension will also be demonstrated in this talk.

Keynote Lecture - I
Arnab Sarkar
Indian Institute of Technology Guwahati, India
Design & Implementation of
Safety-critical Real-time Application
[ 9:30 am, 05-Jun-2018 ]

Methodologies that are currently widely used in the design and implementation of safety-critical real-time application systems are primarily focused on ensuring correctness. This, in conjunction with the trend towards implementing such systems using COTS components, may lead to very poor utilization of the implementation platform resources during runtime. Mixed-criticality implementations have been proposed as one means of achieving more efficient resource utilization upon such platforms, whereby highly safety critical functionalities are implemented upon the same platform as less critical functionalities. Informally speaking, the idea is that, the resources that are provisioned to highly critical functionalities during design time, but are likely to remain unused by these functionalities at run-time, can be “re-claimed” and used to make performance guarantees, albeit at lower levels of assurance, to the less critical functionalities. Recently, the real-time scheduling community has been developing a theory of mixed-criticality scheduling that seeks to solve resource allocation problems for mixed-criticality systems, thereby significantly enhancing our ability to design and implement large, complex, real-time systems in a manner that is both provably correct and resource-efficient.

Keynote Lecture - II
Pradip K. Das
Indian Institute of Technology Guwahati, India
Image Processing: Issues and Trends
[ 12:15 pm, 06-Jun-2018 ]

Emerging Trends in Image Processing, Computer Vision, and Pattern Recognition discusses the latest in trends in imaging science which at its core consists of three intertwined computer science fields, namely: Image Processing, Computer Vision, and Pattern Recognition. There is significant renewed interest in each of these three fields fuelled by Big Data and Data Analytic initiatives including but not limited to; applications as diverse as computational biology, biometrics, biomedical imaging, robotics, security, and knowledge engineering. These three core topics discussed here provide a solid introduction to image processing along with low-level processing techniques, computer vision fundamentals along with examples of applied applications and pattern recognition algorithms and methodologies that will be of value to the image processing and computer vision research communities. Drawing upon the knowledge of recognized experts with years of practical experience and discussing new and novel ideas. Discusses novel applications that can benefit from image processing, computer vision and pattern recognition such as computational biology, biometrics, biomedical imaging, robotics, security, and knowledge engineering. Covers key application techniques in computer vision from fundamentals to mid to high level processing some of which are camera networks and vision, image feature extraction, face and gesture recognition and biometric authentication.