Computer Vision

The research is naturally focused on image analysis and understanding aspects in the large, which are at the basis of all advanced processing. Specific on multiresolution, object recognition, soft computing in image analysis, attentive vision mechanisms with applications to video surveillance, medical imaging, multimedia data treatment.

Pattern Recognition

Research in this field is mainly focused on the probabilistic models for pattern recognition, because of their interesting theoretical properties and their wide applicability in (not only) computer vision tasks. Our interest is mainly in investigating Neural Networks, Markov Random Fields and Kernel Methods. We are interested both in methodological, e.g. learning and model selection, and applicative issues, as shape classification, event detection and classification and clustering, tracking, and video surveillance. Our research is also oriented on very promising non probabilistic techniques, as Support Vector Machines.

Bioinformatics

Currently, more than 55,000 3D structures of some proteins, presenting very similar or identical structures, have been experimentally determined and filed in the Protein Data Bank.
These structures are the building blocks, whose comparison and classification are the basis for studies on development and functional annotation, and have led to many methods for their identification and classification. These often automatic procedures are essential for creation of databases whose classificational reliability is a very critical aspect. The group aims to study novel approaches based on Pattern Recognition and Computer Vision techniques in Bionformatics and Computational Biology. In particular we are interested in the comparison of protein structures, in the search for configurations of common classes of proteins and search for similarities in protein databases.