Subject

Machine vision

Course Title

Machine vision
Machine Vision

Code

F23L3W123

Study Programme

—

Organizer of the study programme (unit, institute, department or division)

Faculty of Computer Science and Engineering

Degree level (first, second, third cycle)

First Cycle

Academic year / semester

7 / Winter

Number of ECTS credits

Teacher

Andrea Kulakov, Ivica Dimitrovski

Prerequisites for enrolling in the course

120 ECTS

10.

Objectives of the course programme (competences)

To introduce students to the basic concepts and techniques in computer vision. Students who successfully
Upon completing the course, they will be able to design efficient computer vision systems such as:
handwriting recognition, face detection and recognition, motion estimation, tracking of people and vehicles,
Gesture recognition, recognition and classification of visual objects, scene understanding and analysis
etc.

11.

Course content

Lectures:
1. Introduction to Computer Vision
2. Cameras and optics. Lighting and color.
3. Pixels and filters.
4. Image processing in the frequency domain. Image pyramids.
5. Edge detection and line matching.
6. Significant points of interest.
7. Descriptions of points of interest.
8. Feature Merging and RANSAC
9. Deep learning
10. Application of deep learning.
11. Facial recognition
12. Latest Topics in Machine Vision.

12.

Learning methods

lectures, classroom exercises, laboratory exercises, project assignments, homework

13.

Total available time

6 ECTS x 30 hours = 180 hours

14.

Distribution of available time

30 + 45 + 15 + 15 + 75 = 180 hours

15.

Forms of teaching activities

15.1.	Lectures - theoretical instruction	30 hours
15.2.	Exercises (laboratory, auditory), seminars, teamwork	45 hours

16.

Other forms of activities

16.1.	Project assignments	15 hours
16.2.	Independent assignments	15 hours
16.3.	Home study	75 hours

17.

Assessment method

17.1.	Tests	30 points
17.2.	Seminar paper / project (presentation: written and oral)	15 points
17.3.	Activities and learning	10 points
17.4.	Final exam	20 points

18.

Grading criteria (points / grade)

up to 50 points	5 (five) (F)
from 51 to 60 points	6 (six) (E)
from 61 to 70 points	7 (seven) (D)
from 71 to 80 points	8 (eight) (C)
from 81 to 90 points	9 (nine) (B)
from 91 to 100 points	10 (ten) (A)

19.

Requirement for obtaining a signature and taking the final exam

Completed activities 15, 16

20.

Language of instruction

Macedonian

21.

Method for monitoring the quality of teaching

internal evaluation and surveys

22.

Literature

22.1.	Required literature 1. Richard Szeliski \| Computer Vision: Algorithms and Applications \| Microsoft Research \| 2010 2. D.A. Forsyth and J. Ponce \| Computer Vision: A Modern Approach \| Prentice Hall \| 2002 3. N. Sebe, M.S. Lew \| Robust Computer Vision: Theory and Applications (Computational Imaging and Vision) \| Springer \| 2003
22.2.	Additional literature No. Author Title Publisher Year