Introduction to Pattern Recognition

Course Description

Pattern recognition. Basic motivation. Pattern recognition model. Examples of pattern recognition systems. Relation: artificial intelligence ? pattern recognition. Feature extraction and selection. Linear and non-linear transformations. Feature coding. Linear decision functions. Non-linear decision functions. Learning procedures for decision functions. Statistical classification. Bayes classifier. Estimation of parameters.Non-numerical pattern recognition. Structural classification. Syntactic recognition. Stochactic Grammars and Languages.Cluster analysis. Examples of pattern recognition system design.

General Competencies

The course “Introduction to Pattern Recognition” enables the students to understand basic concepts of pattern analysis that are used in machine interpretation of a world and environment in which machine works. Pattern recognition is basic building block of understanding human-machine interaction.

Learning Outcomes

  1. define concepts of pattern recognition
  2. explain and distinguish porocedures, methods and algorithms related to pattern recognition
  3. apply methods from the pattern recognition for new applications
  4. analyze and breakdown problem related to the pattern recognition system
  5. design and develop a simple pattern recognition system for the specific application
  6. evaluate quality of solution of the pattern recognition system

Forms of Teaching


Classes are held in two phases - each 7 weeks. Classes are conducted over 15 weeks with a weekly load of three hours. After each phase, ie, in the 8th week of lectures and 15th week of lectures exames are held.Week immediately prior to the exams is scheduled for problem solving and illustrations of procedures.


Knowledge checking is done by written examination twice in a semester. Short ununounced exams are held periodically.


Consultations are planned for 2 hours per week.

Grading Method

By decision of the Faculty Council, in the academic year 2019/2020. the midterm exams are cancelled and the points assigned to that component are transferred to the final exam, unless the teachers have reassigned the points and the grading components differently. See the news for each course for information on knowledge rating.
Continuous Assessment Exam
Type Threshold Percent of Grade Threshold Percent of Grade
Quizzes 0 % 6 % 0 % 0 %
Class participation 0 % 2 % 0 % 0 %
Attendance 85 % 2 % 0 % 0 %
Mid Term Exam: Written 50 % 40 % 50 %
Final Exam: Written 50 % 50 %
Exam: Written 50 % 100 %

Week by Week Schedule

  1. Pattern recognition. Task of pattern recognition. Basic motivation. Example of pattern recognition system.
  2. Model of pattern recognition system.
  3. Linear decision function.
  4. Determining linear decision function. Perceptron algorithm.
  5. Illustration of procedures. Numerical problem solving.
  6. Nonlinear decision functions. Generalized decision functions.
  7. Illustration of procedures. Numerical problem solving.
  8. Midterm exam.
  9. Nonlinear decision functions – potential functions.
  10. Statistical classification. Bayes classifier. Estimation of parameters.
  11. Syntactic (non-numerical) pattern recognition.
  12. Syntactic (non-numerical) pattern recognition. Stochastic grammar. Grammar inference.
  13. Introduction to clustering – unsupervised learning.
  14. Illustration of procedures. Numerical problem solving.
  15. Final exam.

Study Programmes

University undergraduate
Computer Science (module)
Elective Courses (6. semester)
Information Processing (module)
Elective Courses (6. semester)
Software Engineering and Information Systems (module)
Elective Courses (6. semester)


S. Theodoridis, K. Koutroumbas (2009.), Pattern Recogniton, Elsevier
R.O. Duda, P. E. Hart, D.G. Stork (2001.), Pattern Classification, J. Wiley, New York
L. Gyrgyek, N. Pavešić, S. Ribarić (1988.), Uvod u raspoznavanje uzoraka, Tehnička knjiga Zagreb
J.T. Tou, R.C. Gonzalez (1977.), Pattern Recognition Principles, Addison-Wesley


ID 34358
  Summer semester
L1 English Level
L1 e-Learning
45 Lectures
0 Exercises
0 Laboratory exercises
0 Project laboratory

Grading System

89 Excellent
74 Very Good
61 Good
50 Acceptable