Lecture: Computer Vision (Lecture + Practice) - Details

General information

Course name	Lecture: Computer Vision (Lecture + Practice)
Subtitle
Course number	8.3068
Semester	WiSe 2020/21
Current number of participants	99
expected number of participants	150
Home institute	LE Cognitive Science
Courses type	Lecture in category Offizielle Lehrveranstaltungen
First date	Tuesday, 06.10.2020 16:00 - 18:00, Room: 01/B01
Type/Form
SWS	6
Sprache	Englisch
ECTS points	12

Lecturers

• Prof. Dr.-Ing. Gunther Heidemann
• Ulf Krumnack, Ph.D.
• Axel Schaffland, M. Sc.
• Ludwig Schallner, M. Sc.

Tutors

• Luan Wei
• Paul Jänsch
• Sören Selbach
• Marvin Raspini
• Weronika Klos
• Artem Petrov, M. Sc.

Rooms and times

No room preference

Tuesday: 14:00 - 16:00, weekly

Wednesday: 10:00 - 12:00, weekly

Thursday: 10:00 - 12:00, weekly

01/B01

Tuesday, 06.10.2020 - Thursday, 08.10.2020 16:00 - 18:00

Fields of study

• Veranstaltungen > Cognitive Science > Master-Programm
• Veranstaltungen > Cognitive Science > Bachelor-Programm
• Schnupperstudium > Schnupper Uni > Cognitive Science
• Veranstaltungen > Informatik > Importmodule
• Uni für Alle > Cognitive Science

Module assignments

• Bachelor of Science Cognitive Science > CS-BWP-INF - Informatics valid from WiSe 2019/20
• Bachelor of Science Informatik > CS-BWP-NI - Neuroinformatics valid from WiSe 2019/20
• Bachelor of Science Mathematik > CS-BWP-NI - Neuroinformatics valid from WiSe 2019/20
• Bachelor of Science Cognitive Science > CS-BWP-NI - Neuroinformatics valid from WiSe 2019/20
• Master of Science Mathematik > CS-BWP-NI - Neuroinformatics valid from WiSe 2019/20

Comment/Description

Prerequisites: Basic Math

Both the rapid growth of image and video data and new applications such as robotics require automated image processing. This course introduces the basic concepts of artificial vision.
Topics: Image acquisition and representation; mathematical background; basic point operations; linear and nonlinear filtering; morphological pattern recognition; color (perceptual aspects and technical representation); gray-, color- and texture-segmentation; image reconstruction and enhancement; object recognition; compression; applications (e.g., image search in databases). A focus is on object recognition, where topics range from simple edge based methods and template matching over traditional approaches like PCA over Boosting, SIFT and SURF to (deep) neural networks.

Admission settings

The course is part of admission "Anmeldung gesperrt (global)".

The following rules apply for the admission:

• Admission locked.