DEPARTAMENTO DE FÍSICA

 

 - 

Ano letivo: 2007-2008
Specification sheet

Specific details
course codecycle os studiesacademic semestercredits ECTSteaching language
26en


Learning goals
Since early times of computing the design and implementation of algorithms emulating the human
ability to recognize patterns has been found a most intriguing and challenging task.
Pattern Recognition (PR) is the scientific discipline that studies the operation and design of systems that
recognize patterns in data. Important application areas in Computer Science are:
1. Person Identification;
2. Facial Expression Detection;
3. Vehicle Trajectory Recognition;
4. Object Recognition;
5. Mouse Recognition;
6. Handwriting Character Recognition;
7. Speech Analysis;
8. Strategic Games;
9. Pattern Mining in the WEB (WWW, DataWarehouses, Business Intelligence, etc.);
10. Biomedical Data Mining
Syllabus
Pattern Recognition: Concepts, Methods and Applications.
1.Introduction;
2.Statistical Approaches;
3.Neural Networks;
4.Support Vector Machines *
5.Structural Pattern Recognition;
6.Pattern Recognition Project;*
7.Pattern Recognition Software.
Prerequisites
1. Discrete Mathematics, Linear Algebra;
2. Basic Programming and Problem Solving;
3. Programming Languages: C/C++, Python, Matlab, JAVA.
Generic skills to reach
. Competence in analysis and synthesis;
. Computer Skills for the scope of the study;
. Competence to solve problems;
. Capacity of decision;
. Critical thinking;
. Competence in oral and written communication;
. Adaptability to new situations;
. Creativity;
. Competence in applying theoretical knowledge in practice;
. Research skills;
(by decreasing order of importance)
Teaching hours per semester
lectures30
seminar30
other activities2
total of teaching hours62

Assessment
Sseminar or study visit25 %
Project35 %
Exam40 %

Bibliography of reference
Main Bibliography
Marques de Sá, J.P.(2001), Pattern Recognition: Concepts, Methods and Applications, Springer-Verlag.
http://www.amazon.com/Pattern-Recognition-Concepts-Methods-Applications/dp/3540422978
Complementar Bibliography
Duda, R. O., Hart, P.E., and Stork, D.G. (2001). Pattern Classification, 2nd ed. Wiley Interscience, ISBN: 0-471-05669-3.
Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer Verlag
Practical Introduction to Matlab,
http://www.math.mtu.edu/~msgocken/intro/intro.html
Jorge Salvador Marques (2005), Reconhecimento de Padrões: Métodos Estatísticos e Neuronais, 2nd
Ed.,ISBN: 972-8469-08-X,
http://istpress.ist.utl.pt/lrecpad.html
Software:
Statistical Pattern Recognition Toolbox (SPRTool)
http://cmp.felk.cvut.cz/cmp/software/stprtool/
PRTools: The Matlab Toolbox for Pattern Recognition
http://www.prtools.org/
MBP Neural Network Tools
http://dit.ipg.pt/MBP/
Matlab Tutorial
http://www.math.utah.edu/lab/ms/matlab/matlab.html
MATLAB Primer
http://www.math.ucsd.edu/~bdriver/21d-s99/matlab-primer.html
Datasets:
Machine Learning DATASETS
http://archive.ics.uci.edu/ml/
PRTools DataSets
http://eden.dei.uc.pt/~bribeiro/PRTools.rar
Electronic References of Pattern Recognition University Courses on the Web
http://eden.dei.uc.pt/~bribeiro/TRP2010-2011/TRP_Electronic_References.html
Pattern Recognition on the WEB,
http://cgm.cs.mcgill.ca/~godfried/teaching/pr-web.html
Teaching method
Theoretical classes.
Practical Lab Classes.
Seminars.
Pattern Recognition Techniques (TRP) will work partially via Moodle Platform (Foruns, News, Seminars
Discussion, Project Discussion) Link: http://classes.dei.uc.pt/course/view.php?id=16
Above components are essential to successfully obtain the competences and reach the goals of a
Pattern Recognition Course. Namely, the requirements for the design and implementation of the TRP
Project are quite demanding and strongly need to be supported by the learning/teaching methods
described above.
Resources used