Computer Vision

Course Description

The goal of a computer vision system is to create a model of the real world from images. A computer vision system recovers useful information about a scene from its two-dimensional projections.

General Competencies

The course "Computer Vision” enables the students to understand basic, as well as advanced techniques of computer or machine vision that are used in machine interpretation of a world and environment, as well as in reconstruction 3D scenes in which machine works. Computer vision is basic building block of intelligent systems.

Learning Outcomes

  1. define concepts of computer vision and complex systems based on vision
  2. explain and distinguish porocedures, methods and algorithms related to image processing and computer vision.
  3. apply methods from the computer vision for robot vision applications
  4. analyze and breakdown problem related to the computer vision or robot vision system
  5. design and develop the computer or robot vision system for the specific application
  6. evaluate quality of solution of the system based on computer vision

Forms of Teaching


Classes are held in two phases - each 7 weeks. Classes are conducted over 15 weeks with a weekly load of two 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.


Consultations are planned for 2 hours per week.


Groups of 4 to 5 students receive project tasks. The group solves problem, implements the program solution and presents it to the colleagues.

Grading Method

Continuous Assessment Exam
Type Threshold Percent of Grade Threshold Percent of Grade
Seminar/Project 50 % 30 % 0 % 30 %
Mid Term Exam: Written 0 % 30 % 50 %
Final Exam: Written 50 % 40 %
Exam: Written 50 % 70 %

Week by Week Schedule

  1. Basic definitions of computer vision and robot vision.Tasks for a computer vision. Relation between biological, robot vision systems and relation to other fields.
  2. Image formation:Sampling lattices, Reciprocal lattices, 2D Shannon theorem
  3. Image geometry, Perspective projection, Model of camera.
  4. Calibration procedures. Stero imaging. Image input and representation in a computer.
  5. Binary image processing. Thresolding. Uspoređivanje s pragom. Histogram. Discrete binary image. Template maching.Topological properties of image. Size, position and orientation of object. Component labeling.
  6. BF-algorithm. Fourier coefficients. Granlund descriptors. Moments.
  7. Illustration of procedures and problem solving.
  8. Midterm exam
  9. Image segmentation. Region segmentation. Split and Merge method. Otsu method for threshold selection. Heuristic methods. Region representation.
  10. Edge segmentation. Gaussian. Sobel and compass operators. Canny operator. LoG operator.
  11. Illustration of procedures and problem solving.
  12. Border detection.Hough transform. Generalized Hough transform.
  13. Image Understanding Models. Hierarchical and Hetrrarchical Models. Blackboard model. Description formalisms. Knowledge representation in robot and computer vision systems.
  14. Illustration of procedures and problem solving.
  15. Final exam.

Study Programmes

University graduate
Computer Engineering (profile)
Recommended elective courses (3. semester)
Computer Science (profile)
Specialization Course (1. semester) (3. semester)
Information Processing (profile)
Specialization Course (1. semester) (3. semester)


M. Nixon, A. Aguado (2008.), Feature Extraction&Image Processing, Elsevier
D. A. Forsyth, J. P. Ponce (2003.), Computer Vision: A Modern Approach, Prentice Hall
R. Jain, R. Kasturi, B. G. Schunck (2003.), Machine Vision, Pearson-Prentice Hall

Grading System

ID 34416
  Winter semester
L1 English Level
L1 e-Learning
30 Lecturers
0 Exercises
0 Laboratory exercises


89 Excellent
74 Very Good
61 Good
50 Acceptable