John R. Smith is Senior Manager of the Intelligent Information Management Dept. at the IBM T. J. Watson Research Centre. He received his Ph.D. in Electrical Engineering from Columbia University in 1997. His research interests include multimedia databases, content analysis, compression, indexing, and retrieval. In 2003, Dr. Smith was co-recipient of the "Multimedia Prize" for best paper in IEEE Trans. Multimedia over the previous four-year period. Dr. Smith was also co-editor of MPEG-7 Multimedia Metadata Standard and Chair of MPEG Multimedia Description Schemes (MDS) group. He currently leads IBM's Marvel multimedia analysis and retrieval research project.

Discussing: Promises and Challenges of Machine Tagging of Large Multimedia Repositories

New digital multimedia content is being generated at a tremendous rate. However, users are still finding it difficult to find relevant content. Today’s techniques are not keeping up with the explosion of content. Manually tagging by professionals is only best suited for content with very high value. Alternatively, social tagging of consumer content by end-users results in ambiguity due to lack of vocabulary control. Automated machine tagging techniques hold great promise for improving indexing of high-value content as well as consumer content. They also address the wide range of content in between corresponding to deep media archives. New techniques are emerging based on statistical machine learning and semantic concept ontologies that effectively model and tag multimedia contents. We are developing the Marvel system which applies these modelling techniques across extracted audio, speech and visual content for automatically tagging video. The benefit is a reduction in manual processing and enhanced ability to unlock the value of large multimedia repositories.

He worked at the University of California, Berkeley and the University of Maryland, College Park in 1986-87; the NASA Johnson Space Center, Houston, Texas in 1990-92 & 1994; and in US Naval Research Laboratory, Washington DC in 2004. Since 1997 he has been serving as a Distinguished Visitor of IEEE Computer Society (USA) for the Asia-Pacific Region, and held several visiting positions in Hong Kong and Australian universities.

Prof. Pal is a Fellow of the IEEE, USA, The Academy of Sciences for the Developing World (TWAS), Italy, International Association for Pattern Recognition, USA, and all the four National Academies for Science/ Engineering in India. He is a co-author of thirteen books and about three hundred research publications in the areas of Pattern Recognition and Machine Learning, Image Processing, Data Mining and Web Intelligence, Soft Computing, Bioinformatics Neural Nets, Genetic Algorithms, Fuzzy Sets, Rough Sets, and Bioinformatics.

He has received the 1990 S.S. Bhatnagar Prize (which is the most coveted award for a scientist in India), and many prestigious awards in India and abroad including the 1999 G.D. Birla Award, 1998 Om Bhasin Award, 1993 Jawaharlal Nehru Fellowship, 2000 Khwarizmi International Award from the Islamic Republic of Iran, 2000-2001 FICCI Award, 1993 Vikram Sarabhai Research Award, 1993 NASA Tech Brief Award (USA), 1994 IEEE Trans. Neural Networks Outstanding Paper Award (USA), 1995 NASA Patent Application Award (USA), 2005-06 Indian Science Congress- P.C. Mahalanobis Birth Centenary Award (Gold Medal) for Lifetime Achievement, 1997 IETE-R.L. Wadhwa Gold Medal, and the 2001 INSA-S.H. Zaheer Medal.

Prof. Pal is an Associate Editor of IEEE Trans. Pattern Analysis and Machine Intelligence (2002-06), IEEE Trans. Neural Networks (1994-98, 2003-06), Pattern Recognition Letters, Int. J. Pattern Recognition and Artificial Intelligence, Neurocomputing (1995-2005), Applied Intelligence, Information Sciences, Fuzzy Sets and Systems, Fundamenta Informaticae, Int. J. Computational Intelligence and Applications, and Proc. INSA-A; a Member, Executive Advisory Editorial Board, IEEE Trans. Fuzzy Systems, Int. Journal on Image and Graphics, and Int. Journal of Approximate Reasoning; and a Guest Editor of IEEE Computer.

Discussing: Rough-fuzzy Granulation, Rough Entropy and Image Segmentation

This talk has two parts. The first part describes how the concept of rough-fuzzy granulation can be used for the problem of case generation, with varying reduced number of features, in a case based reasoning system, and their application to multi-spectral image segmentation. Here the synergistic integration of EM algorithm, minimal spanning tree and granular computing for efficient segmentation is described. The second part deals with defining a new definition of image entropy in a rough set theoretic framework, and its application to the object extraction problem from images by minimizing both object and background roughness. Granules carry local information and reflect the inherent spatial relation of the image by treating pixels of a window as indiscernible or homogeneous. Maximization of homogeneity in both object and background regions during their partitioning is achieved through maximization of rough entropy; thereby providing optimum results for object background classification. The effect of granule size is also discussed.
Key Words: Image processing, clustering, soft computing, granular computing, EM algorithm, minimal spanning tree, multi-spectral image segmentation

Prof. Izquierdo received the Dr. Rerun Naturalium (PhD) from the Humboldt University, Berlin, Germany, in 1993. From 1990 to 1992 he was a teaching assistant at the department of applied mathematics, Technical University Berlin. From 1993 to 1996 Dr. Izquierdo was with the Heinrich-Hertz Institute for Communication Technology (HHI), Berlin, Germany, as associated researcher.

Since 1993, Dr. Izquierdo has been involved in research and management of projects in Germany, the UK and the EU. Dr. Izquierdo was the UK representative of the EU Action Cost211 and currently coordinates the EU Action Cost292 and the Network of Excellence K-Space. He has also coordinated the EU IST project BUSMAN and is a main contributor to the IST IP aceMedia.

Dr. Izquierdo is associate editor of the IEEE Transactions on Circuits and Systems for Video Technology and has served as guest editor of two special issues of the IEEE TCSVT. He has published over 150 technical papers including chapters in books.

Shailesh was awarded the Dr Shankar Dayal Sharma Gold medal for his M Tech from the Indian Institute of Technology, Kharagpur, and received his B.E. from VJTI, Bombay.
He has delivered several well received tutorials and talks on the subject, including ISCAS-2002, ICMW and SPCOM 2001.