Research In Multimedia Systems Research Articles

Editorial: In Memoriam: Anastasios (Tas) N. Venetsanopoulos

On November 17, 2014, the signal processing world lost Anastasios N. Venetsanopoulos. Tas, as he was known to his friends and colleagues, had a long and prolific career that spanned over 40years, wherein he established himself as an internationally renowned and respected researcher, a prolific author and an exceptionally gifted educator. Tas was widely regarded as a world authority and a pioneer of the signal processing field. Specifically, his research in multimedia systems, digital signal and image processing, digital communications, biometrics and neural networks is internationally acclaimed, both in academia and industry, and resulted in nine books (including [1–4]), 35 book chapters and 900 technical papers with over 14,000 citations. He was a mentor to over 160 graduate students and researchers and an educator to thousands of undergraduate students while serving, with distinction, in a number of key administrative positions within the University of Toronto and Ryerson University, both in Toronto, Canada. Tas earned his Bachelor of Electrical and Mechanical Engineering degree from the National Technical University of Athens in 1965, and a Master of Applied Science, a Master of Philosophy and a Doctor of Philosophy in Electrical Engineering from Yale University in 1966, 1968 and 1969, respectively. He joined the Department of Electrical Engi-

Multimedia systems research

This retrospective article examines the past two decades of multimedia systems research through the lens of three research topics that were in vogue in the early days of the field and offers perspectives on the evolution of these research topics. We discuss the eventual impact of each line of research and offer lessons for future research in the field.

Bringing High Level Meanings from an Image

Content-based image retrieval is a difficult area of research in mult imedia systems. The research has proved extremely difficult because of the inherent problems in proper auto mated analysis and feature extract ion of the image to facilitate proper classificat ion of various objects. To segment the image to ext ract mean ingful objects and then classify it in high-level like table, chair, car and so on has become a challenge to the researchers in the field. The gap between low-level features like color, shape, texture, spatial relat ionships and high-level definit ions of the images is called the semantic gap. It is very important we find a viable solution of how to ext ract meaningful definition of an image fro m low level features so that we can identify the image automatically without any human intervention. As we know billions of images are being generated fro m various sources all over and it's extremely time consuming and expensive to identify these images manually. When we can identify these vast number of images automatically without human intervention then we can classify them and create databases based on these classifications. These databases could then be used to enhance mach ine learning of artificial intelligence. Until we solve these problems in an effective way, the efficient processing and retrieval of info rmation fro m images will be difficu lt to achieve. In this paper we explore the possibilities of how we can ext ract high-level meanings fro m an image before or after the seg mentation of the image in an automat ized way. We attempt to use a database of data dictionary for the purpose which we believe has the potential for solving the problem of semantic gap in content-based image ret rieval.

MediaBench II video: Expediting the next generation of video systems research

The first step towards the design of video processors and systems is to achieve an understanding of the major applications, including not only the theory, but also the workload characteristics of the many image and video compression standards. Introduced in 1997, the MediaBench benchmark suite provided the first set of full application-level benchmarks for multimedia, and has consequently enabled significant research in computer architecture and compiler research for media systems. To expedite the next generation of multimedia systems research, we are developing the MediaBench II benchmark suite, incorporating benchmarks from the latest multimedia technologies, and providing both a single composite benchmark suite ( MB 2 comp ) as well as separate sub-suites for each area of multimedia. For video, MediaBench II Video ( MB 2 video ) includes both the popular mainstream video compression standards, such as JPEG, H.263, and MPEG-2, and the more recent and emerging standards, including MPEG-4, JPEG-2000, and H.264. This paper first discusses the goals for MediaBench II and the design of the MB 2 video sub-suite. The paper then presents the results of a comprehensive workload evaluation of MB 2 video . In particular, while the workload evaluation demonstrates the high processing regularity of video workloads, as compared with general-purpose workloads, it also illustrates how the growing complexity of the emerging video standards is beginning to negatively impact video workload characteristics.

Research in multimedia systems at DFKI

The German Research Center for Artificial Intelligence (Deutsches Forschungszentrum fur Kunstliche Intelligenz, DFKI) is a non-profit organization that conducts application-oriented basic research in the field of Artificial Intelligence and other related subfields of computer science. One of its current research areas is devoted to Intelligent User Interfaces. The group, headed by Prof. Dr. Wolfgang Wahlster, is concerned with issues of multimedia/multimodal communication. In this paper, an overview of two projects carried out by the group is given.