This Seminar sponsored by EURASIP is held in the framework of the Second IEEE SPS Italy Chapter Summer School on Signal Processing, Frascati (RM) - Italy - July 7-11, 2014
Speaker: Prof. Josef Kittler, University of Surrey, United Kingdom
When: July 8, 2014 at 9.00-12.30
An important capability of sensor based systems for monitoring, controlling, supporting human decision making, or even fully automatic operation is to detect anomalous situations, flagging an attention warranting event posing a threat or placing the operational system beyond the limits of its competence. With the ever increasing level of intelligence and functional sophistication of sensor based systems, anomaly detection has also grown in complexity, taking into account contextual information and multimodal input to detect anomalous events. However, by and large, the conceptual basis of existing anomaly detection systems to date draws on the conventional formulation of anomaly detection as an outlier detection problem. The course will discuss recent advances in the field, which engage more complex mechanisms for anomaly detection. Anomaly detection will be introduced as a problem in statistical hypothesis testing. An architecture of an anomaly detection system overcoming the deficiencies of outlier detection will then be presented. It involves a number of other essential mechanisms, including classifier incongruence detection, data quality assessment, classifier confidence, and model drift gauging. The discussion of classifier incongruence detection will cover histogram comparison and Bayesian surprise measures, as well as their estimation error sensitivity.
Professor Josef Kittler heads the Department of Electronic Engineering at the Faculty of Engineering and Physical Sciences, University of Surrey. He received his BA, PhD and DSc degrees from the University of Cambridge. He teaches and conducts research in the subject area of Signal Processing and Machine Intelligence, with a focus on Biometrics, Video and Image Database retrieval, Automatic Inspection, Medical Data Analysis, and Cognitive Vision. He published a Prentice Hall textbook on Pattern Recognition: A Statistical Approach and several edited volumes, as well as more than 700 scientific papers, including in excess of 150 journal papers. He serves on the Editorial Board of several scientific journals in Pattern Recognition and Computer Vision. He became Series Editor of Springer Lecture Notes on Computer Science in 2004. He served as President of the International Association for Pattern Recognition 1994-1996. He was elected Fellow of the Royal Academy of Engineering in 2000. In 2006 he was awarded the KS Fu Prize from the International Association in 2006, for outstanding contributions to pattern recognition. He received Honorary Doctorates from the University of Lappenranta in 1999 and the Czech Technical University in Prague in 2007. In 2008 he was awarded the IET Faraday Medal and in 2009 he became EURASIP Fellow.