BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Classifier Combination with Quality Measures 
DTSTART:20100324T091500
DTSTAMP:20260407T002628Z
UID:4aa1ecc536d5f4194b429c1210f564827dc47b4e35c83cd927883c4b
CATEGORIES:Conferences - Seminars
DESCRIPTION:Norman Poh\nSensory information acquired by pattern recognitio
 n systems is invariably subject to environmental and sensing conditions\, 
 which may change over time. This may have a significant negative impact on
  the performance of pattern recognition algorithms.\n\nIn the past\, these
  problems have been tackled by building in invarianceto the various change
 s\, by adaptation and by multiple expert systems. Morerecently\, the possi
 bility of enhancing the pattern classification system robustnessby using a
 uxiliary information has been explored. In particular\, by measuring the e
 xtent of degradation\, the resulting sensory data quality information can 
 be used with advantage to combat the effect of the degradation phenomena. 
 This can be achieved by using the auxiliary quality information as feature
 s in the fusion stage of a multiple classifier system which uses the discr
 iminant function values from the first stage as inputs. Data quality can b
 e measured directly from the sensory data. \n\nDifferent architectures hav
 e been suggested for decision making using quality information. Examples o
 f these architectures are presented and their relative merits discussed. T
 he problems and benefits associated with the use of auxiliary information 
 in sensory data analysis are illustrated on the problem of personal identi
 ty verification in biometrics.\n\nNorman Poh is a research fellow at CVSSP
 \, University of Surrey\, since 2006\, after having  completed the Ph.D. d
 egree in computer science conferred by the Swiss Federal Institute  of Tec
 hnology in Lausanne (EPFL).  He is one of the work-package leaders in the 
 EU-funded  Mobile Biometry (MOBIO) project (led by IDIAP)\, responsible fo
 r designing adaptive multimodal  biometric systems. His areas of interest 
 are pattern recognition\, video processing\, biometric authentication\, an
 d information fusion\, and he has authored in excess of 50 peer-reviewed  
 publications. He was the recipient of three best paper awards (AVBPA'05\, 
 ICB'09 and  Pattern Recogition Journal\, 2006) and two personal research g
 rants from the  Swiss National Science Foundation.
LOCATION:BC 04 https://plan.epfl.ch/?room==BC%2004
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR