PhD Seminar Course on

Issues and Challenges on Multimodal Biometrics

Cagliari, Oct. 15 -- Oct. 23, 2009


Prof. Norman Poh    
University of Surrey, Guildford, Surrey, UK


8 hours, Oct. 15 -- Oct. 23, 2009


Lecture 1 (2 hours):    Friday,             14:00 --- 16:00,     Oct. 16

Lecture 2 (2 hours):    Monday,          10:00 --- 12:00,     Oct. 19

Lecture 3 (2 hours):    Wednesday,     10:00 --- 12:00,     Oct. 21

Lecture 4 (2 hours):    Friday,             10:00 --- 12:00,     Oct. 23


Mocci Classroom (DIEE, Building A)


This course aim to arm the participants by hand-crafing a Bayesian classifier using both generative and discriminative approaches. Advanced topics such as dealing with missing values and Bayesian network are also covered. These techniques enable one to solve many machine-learning problems where training data is an integral part of the system design. Practical applications are illustrated via multimodal information fusion in biometrics.
The course (8 lecture hours) will be roughly structured as shown below:   

  1. Lecture 1: Decision theory, generative and discriminative classifiers, Naive Bayes

  2. Lecture 2: Error prediction in multimodal information fusion

  3. Lecture 3: User-specific score normalization and fusion

  4. Lecture 4: Quality-based fusion

Lectures 2-4 have example applications applied to biometrics.


Ing. Gian Luca Marcialis
Dep. of Electrical and Electronic Engineering
University of Cagliari, Italy
Email: marcialis[at]