PA228 Machine Learning in Image Processing

Faculty of Informatics
Spring 2025
Extent and Intensity
2/2/1. 4 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: z (credit).
In-person direct teaching
Teacher(s)
doc. RNDr. Petr Matula, Ph.D. (lecturer)
Mgr. Lucia Hradecká (seminar tutor)
doc. RNDr. Martin Maška, Ph.D. (seminar tutor)
doc. RNDr. David Svoboda, Ph.D. (seminar tutor)
Nikomidisz Jorgosz Eftimiu, M.Sc. (assistant)
Aleksandra Melnikova (assistant)
Guaranteed by
doc. RNDr. Petr Matula, Ph.D.
Department of Visual Computing – Faculty of Informatics
Supplier department: Department of Visual Computing – Faculty of Informatics
Prerequisites
It is recommended to have a basic knowledge of image processing (at least at the level of course PB130), the knowledge of neural networks at the level of course PV021, and basic knowledge of Python.
Course Enrolment Limitations
The course is also offered to the students of the fields other than those the course is directly associated with.
The capacity limit for the course is 50 student(s).
Current registration and enrolment status: enrolled: 0/50, only registered: 2/50, only registered with preference (fields directly associated with the programme): 0/50
fields of study / plans the course is directly associated with
Course objectives
The objective of the course is to introduce approaches for solving common image processing problems using machine learning methods.
Learning outcomes
At the end of the course students should be able to: understand, use, and evaluate machine learning models in the area of image processing; know how to employ pre-trained models using transfer learning; how to deal with big datasets that do not fit available memory; and how to prepare data to get relevant results.
Syllabus
  • Image classification
  • Object detection
  • Semantic segmentation
  • Instance segmentation
  • Image generation
  • Style transfer
  • Image captioning
  • Image inpainting
  • Video processing
Literature
  • PLANCHE, Benjamin and Eliot ANDERS. Hands-On Computer Vision with TensorFlow 2: Leverage deep learning to create powerful image processing apps with TensorFlow 2.0 and Keras. Packt Publishing, 2019. ISBN 1-78883-064-4. info
Teaching methods
Lectures followed by class exercises in a computer room to gain hands-on experience.
Assessment methods
Mandatory practicals (labs) on computers with a mandatory semestral project. Written final exam with an optional oral part.
Language of instruction
English
Further Comments
The course is taught annually.
The course is taught: every week.
The course is also listed under the following terms Spring 2022, Spring 2023, Spring 2024.
  • Enrolment Statistics (Spring 2025, recent)
  • Permalink: https://is.muni.cz/course/fi/spring2025/PA228