Computer Vision technologies

The discipline is aimed at providing a solid theoretical foundation and strong practical skills in the software implementation of methods, mathematical models, and algorithms of Computer Vision technologies.

The theoretical foundations of Computer Vision are delivered through lectures with mandatory demonstrations of practical implementations of the studied algorithms in the form of program code examples.

Practical skills in applying Computer Vision technologies are acquired during laboratory sessions, which are structured on the principle of incrementally extending the functionality of developed scripts. Particular attention is paid to software engineering processes.

The practical part of the discipline focuses on the use of the high-level programming language Python, including the study of graphical libraries such as Graphics, Tkinter, Matplotlib, and NumPy (for “raw” implementation of Computer Vision algorithms), as well as specialized packages such as PIL/Pillow, OpenGL, and OpenCV for developing complete, application-oriented software modules.

The discipline reveals the essence of the stages of the classical digital image processing pipeline: image synthesis (spatial transformation) – rasterization (realistic image, digital processing) – vectorization (object identification and target image processing).

The course is oriented toward the needs of positions such as Software Developer with Computer Vision, Embedded Developer for Computer Vision systems, and Computer Vision Research Engineer.

Lecturer:

Pysarchuk Oleksii Oleksandrovych