Course detail
Computer Vision (in English)
FIT-POVaAcad. year: 2018/2019
Principles and methods of computer vision, methods and principles of image acquiring, preprocessing methods (statistical processing), filtering, pattern recognition, integral transformations - Fourier transform, image morphology, classification problems, automatic classification, D methods of computer vision, open problems of computer vision.
Supervisor
Nabízen zahradničním studentům
Všech fakult
Learning outcomes of the course unit
The students will get acquainted with the principles and methods of computer vision. They will learn in more detail selected methods and algorithms of vision and image acquiring. They will also get acquainted with the possibilities of the scanned data processing. Finally, they will learn how to apply the gathered knowledge practically.
The students will improve their teamwork skills, mathematics, and exploitation of the "C" language.
Prerequisites
Not applicable.
Co-requisites
Not applicable.
Recommended optional programme components
Not applicable.
Recommended or required reading
- Russ, J.C.: The IMAGE PROCESSING Handbook, CRC Press, 1995, ISBN 0-8493-2532-3
- Bass, M.: Handbook of Optics, McGraw-Hill, New York, USA, 1995, ISBN 0-07-047740-X
- Horn, B.K.P.: Robot Vision, McGraw-Hill, 1988, ISBN 0-07-030349-5
- Hlaváč, V., Šonka, M.: Počítačové vidění, Grada, 1993, ISBN 80-85424-67-3
- Russ, J.C.: The IMAGE PROCESSING Handbook, CRC Press, 1995, ISBN 0-8493-2532-3
- Bass, M.: Handbook of Optics, McGraw-Hill, New York, USA, 1995, ISBN 0-07-047740-X
Planned learning activities and teaching methods
Not applicable.
Assesment methods and criteria linked to learning outcomes
Homeworks, Mid-term test, individual project.
Language of instruction
English
Work placements
Not applicable.
Course curriculum
- Syllabus of lectures:
- Úvod, základy, motivace a aplikace/Introduction, motivation and applications (Zemčík 18.9. slajdy, slajdy, highlights)
- 28.9. přednáška není/no lecture :-(
- Základní principy klasifikace s učitelem - AdaBoost/Basic principles of machine learning with teacher - AdaBoost (Zemčík 5.10. slajdy-cz, slajdy-en)
- Shlukování, statistické metody/Clustering, statistical methods (Španěl 12.10. slajdy)
- Segmentace, analýza barev, analýza histogramu/Segmentation, colour analysis, histogram analysis (Španěl 19.10. slajdy1, slajdy2, slajdy3)
- Analýza a extrakce příznaků z textur/Analysis and Feature Extraction from Images (Čadík 26.10. slajdy)
- Hough transform, RHT, RANSAC, zpracování časových sekvencí/Time Sequence Processing (Hradiš, 2.11. slajdy1, slajdy2, slajdy2-en)
- Segmentace, analýza barev/Segmentation, Colour Analysis, ... finishing (Španěl), Object Detection - Trees (Juránek, 9.11. slajdy1, slajdy2)
- Test, Invariantní Oblasi Obrazu/Invariant Image Regions (Beran, 16.11. slajdy)
Aims
To get acquainted with the principles and methods of computer vision. To learn in more detail selected methods and algorithms of vision and image acquiring. To get acquainted with the possibilities of the scanned data processing. To learn how to apply the gathered knowledge practically.
Classification of course in study plans
- Programme IT-MGR-2 Master's
branch MBI , any year of study, winter semester, 5 credits, elective
branch MPV , any year of study, winter semester, 5 credits, compulsory-optional
branch MGM , any year of study, winter semester, 5 credits, compulsory-optional - Programme IT-MGR-2 Master's
branch MGMe , any year of study, winter semester, 5 credits, compulsory-optional
- Programme IT-MGR-2 Master's
branch MSK , any year of study, winter semester, 5 credits, elective
branch MBS , any year of study, winter semester, 5 credits, elective
branch MIN , any year of study, winter semester, 5 credits, compulsory-optional
branch MMM , any year of study, winter semester, 5 credits, elective - Programme IT-MGR-1H Master's
branch MGH , any year of study, winter semester, 5 credits, recommended
- Programme IT-MGR-2 Master's
branch MIS , 2. year of study, winter semester, 5 credits, elective
Type of course unit
Lecture
26 hours, optionally
Teacher / Lecturer
Syllabus
- Úvod, základy, motivace a aplikace/Introduction, motivation and applications (Hradiš 20.9. slajdy, slajdy, highlights)
- Základní principy klasifikace s učitelem - AdaBoost/Basic principles of machine learning with teacher - AdaBoost (Zemčík 27.9. slajdy-cz, slides-en)
- Shlukování, statistické metody/Clustering, statistical methods (Španěl 4.10. slajdy)
- Segmentace, analýza barev, analýza histogramu/Segmentation, colour analysis, histogram analysis (Španěl 11.10. slajdy1, slajdy2, slajdy3)
- Segmentace, analýza barev/Segmentation, Colour Analysis, ... finishing (Španěl), Object Detection - Trees (Juránek, 18.10. slajdy-en)
- Analýza a extrakce příznaků z textur/Analysis and Feature Extraction from Images (Čadík 25.10. slajdy)
- Hough transform, RHT, RANSAC, zpracování časových sekvencí/Time Sequence Processing (Hradiš, 1.11. slajdy1, slajdy2, slajdy2-en)
- Invariantní Oblasi Obrazu/Invariant Image Regions (Beran, 8.11. slajdy)
- Test, Konvoluční neuronové sítě a Tagování obrazu/Convolutional Neural Networks and Automatic Image Tagging (Hradiš, 15.11. slajdy )
- Konvoluční neuronové sítě a Tagování obrazu/Convolutional Neural Networks and Automatic Image Tagging II (Hradiš, 22.11. slajdy )
- Registrace obrazu (Čadík, 29.11., slajdy)
- 3D Vision/3D Vidění (6.12. Richter FEKT slajdy)
- Akcelerace zpracování obrazu, závěr (Zemčík, 13.12.)
POZOR!!! Témata přednášek i data jsou orientační a budou v průběhu semestru aktualizována.
NOTE: The topics and dates are just FYI, not guaranteed, and will be continuously updated.
Project
26 hours, compulsory
Teacher / Lecturer
Syllabus
- Homeworks (4-5 runs) at the beginning of semester
- Individually assigned project for the whole duration of the course.