Professor: Jacob Scharcanski
Hours: 60 hs
Semesters: Second semester
Undergraduate Enrollment: The enrollment must be made as Special Student
Page Link: –
Introduction to Pattern Recognition; Bayesian decision theory; Maximum likelihood and
Bayesian estimation; Non-parametric techniques and linear discriminant function;
Stochastic and pattern recognition methods; graphic (graph-based) models; Clustering.
This course will introduce the fundamentals of statistical pattern recognition with examples
from several application areas. Techniques for handling multidimensional data of various
types and scales along with algorithms for clustering and classifying data will be explained.
This is an graduate level course suited for graduate students in Computer Science and
Engineering. It is primarily intended for highly motivated graduate students who are
interested in doing research in the areas of Pattern Recognition, Artificial Intelligence,
Image Processing, Graphics and Computer Vision. Many open problems in these areas
suitable for investigation by Master’s or Ph.D. students will be presented and proposed.
• Introduction to Pattern Recognition
• Bayesian Decision Theory
• Maximum Likelihood and Bayesian Estimation
• Non-Parametric Techniques and Linear Discriminant Functions
• Stochastic Methods and Pattern Recognition (Selected Topics)
• Graphic (Graph-Based) Models in Pattern Recognition
• Clustering (Selected Topics)
Basic knowledge of probability and statistics, strong programming skills (e.g. MATLAB),
and linear algebra. Courses on artificial intelligence, image processing, computer vision,
and machine learning would be helpful but not required.
Grading will be based on three projects involving programming and presentation. The
material covered by the projects will be drawn from the material covered in class. The
topics of the projects should be related to the application of a pattern recognition technique
(i.e., preferably state-of-the-art) to practical problems (e.g. artificial intelligence or
computer vision). Each presentation should be professional as if it was presented in a
formal conference (i.e., slides/projector). Late projects will not be accepted after the second
class following the deadline (the project weight will be decreased by 50% if delivered in
the first class after the deadline). If you are unable to deliver a project by the deadline, you
must discuss it with the instructor before the deadline. Please, note that good programming
skills and strong motivation would be essential in order to complete the projects.
• R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, Wiley-Interscience.
• K. Fukunaga, Statistical Pattern Recognition, 2nd edition, Morgan Kaufmann, 1990
• T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning: Data Mining,
Inference and Prediction, Springer-Verlag, 2009.
• Selected papers (e.g.: IEEE PAMI, CVPR, etc.)