Pattern Recognition and Scene Analysis via Machine Learning. We plan to use kernel methods, a novel machine learning technique, for computer vision problems, such as scene analysis and real time object recognition. Such capabilities are relevant for the design of intelligent and adaptive systems, suitable for complex real world environments. Expected outcomes are the design of efficient statistical tools which take the special nature of visual data into account (structure, decomposition, prior ....Pattern Recognition and Scene Analysis via Machine Learning. We plan to use kernel methods, a novel machine learning technique, for computer vision problems, such as scene analysis and real time object recognition. Such capabilities are relevant for the design of intelligent and adaptive systems, suitable for complex real world environments. Expected outcomes are the design of efficient statistical tools which take the special nature of visual data into account (structure, decomposition, prior knowledge of physical environments, etc.) and combine the advantages of feature based high-level vision methods with low-level machine learning techniques.
This proposal is part of a joint IST project with partners from the European Union.Read moreRead less
Sharing Complex Systems information by challenging the orthodoxies of linear presentation. Information Technology has contributed more to working with complex systems than to communicating them. Presentation software styled on the power of the point hardly addresses the restrictions of traditional media: sequential visual information display with little possibility for the cross-reference needed to communicate a complex situation.
This research will test the effectiveness of our multidimension ....Sharing Complex Systems information by challenging the orthodoxies of linear presentation. Information Technology has contributed more to working with complex systems than to communicating them. Presentation software styled on the power of the point hardly addresses the restrictions of traditional media: sequential visual information display with little possibility for the cross-reference needed to communicate a complex situation.
This research will test the effectiveness of our multidimensional presentation software prototype in a range of complex system situations in order to improve the opportunities for interactive spatial media in today's work and learning environments.
Read moreRead less