Machine vision fundamentals | Faculty of Technical Sciences

Subject: Machine vision fundamentals (17.H1420)

Native organizations units: Department of Power, Electronic and Telecommunication Engineering

Type of studies	Title
Master Academic Studies	Mathematics in Engineering (Year: 2, Semester: Winter)
Master Academic Studies	Mechatronics (Year: 1, Semester: Winter)

General information:

Category	Theoretical-methodological
Scientific or art field	Telecommunications and Signal Processing
ECTS	4

Understanding of fundamental concepts in the field of machine vision; Becoming familiar with up-to-date methods in this field through work on several projects.

Overview of the principles of modern methods in machine vision. Participants should be able to understand fundamental concepts and methods that are used in digital image processing and machine vision, acquire capability to independently implement simple systems for digital image processing, as well as become able to easily expand knowledge through further work on a certain problem.

Introduction to digital image processing – Fundamental concepts in image processing – Image improvement in spatial domain – Image improvement in frequency domain – Image restoration – Colour image processing – Morphological image processing – Image segmentation – Pattern recognition and machine learning in machine vision – Analysis and application of different models of shallow and deep neural networks in machine vision tasks.

Lectures; Computer laboratory exercises; Consultations; Presentations; Demonstrations; Course projects. Course is attended through standard teaching forms and includes obligatory attendance at lectures and computer laboratory exercises.

Authors	Title	Year	Publisher	Language
Aggarwal, C.	Neural networks and deep learning	2018	Springer	English
Bovik A.	Handbook of image and video processing	2005	Academic Press	English
Gonzalez, R.C., Woods, R.E.	Digital Image Processing (3rd Edition)	2008	Prentice-Hall, Inc., Upper Saddle River	English
Szeliski, R.	Computer vision: algorithms and applications	2011	Springer, London	English
Kaehler A., Bradski G.	Learning OpenCV 3: Computer vision in C++ with the OpenCV library	2016	OReilly	English
Sonka, M., Hlavac, V., Boyle, R.	Image Processing, Analysis and Machine Vision	2008	Thompson Learning, Toronto	English
Das A.	Guide to signals and patterns in image processing	2015	Springer	English
Ramsundar B., Zadeh R.	TensorFlow for deep learning	2018	OReilly	English
Davies E.	Machine vision - Theory, algorithms, practicalities	2005	Morgan Kaufmann	English
Krig, S.	Computer Vision Metrics Survey, Taxonomy, and Analysis	2014	Apress Media	English

Course activity	Pre-examination	Obligations	Number of points
Theoretical part of the exam	No	Yes	60.00
Project	Yes	No	30.00
Presentation	Yes	Yes	10.00
Test	Yes	Yes	10.00
Computer exercise attendance	Yes	Yes	5.00
Coloquium exam	No	No	30.00
Test	Yes	Yes	10.00
Lecture attendance	Yes	Yes	5.00
Coloquium exam	No	No	30.00