News

Lecture 4 moved to Thursday, April 17, 18:15

Written on 11.04.25 (last change on 11.04.25) by Karl Schrader

The fourth lecture, originally planned for Friday, April 18, collides with a federal holiday (Good Friday/Karfreitag). As such, we are moving it to Thursday, April 17, 18:15, via the usual Zoom link found at Information -> Materials.

We encourage live participation to allow you to ask… Read more

We encourage live participation to allow you to ask questions, but will also provide a video recording.

To allow you the full seven days to work on the homework assignment, we have extended the submission deadline for Homework Assignment H1 to Tuesday, April 22, 10:15 - just before Lecture 5. The sample solution will also be released at that time.

Correction: Form submission group till Friday, April 25, 10:15

Written on 11.04.25 by Karl Schrader

In the last CMS news, I had announced a wrong date for the deadline to form submission groups. The correct date, as it was also announced in the lecture today, is Friday, April 25, 10:15.

I would also like to remind you that all students in a submission group have to be part of the same tutorial.

Tutorials have been assigned

Written on 11.04.25 (last change on 11.04.25) by Karl Schrader

Everybody has now been assigned to a tutorial based on their preferences and availability as selected during registration for the course. You can find your tutorial on your Personal Status page.

All groups which were formed before the tutorial assignment were preserved, all group members were… Read more

Everybody has now been assigned to a tutorial based on their preferences and availability as selected during registration for the course. You can find your tutorial on your Personal Status page.

All groups which were formed before the tutorial assignment were preserved, all group members were always placed in the same tutorial. Until Friday, April 25, you still have the option to build groups of up to three students from the same tutorial to work on the homework sheets and to hand in your solutions together.

Note that arbitrary changes of your tutorial slot are not possible.

If you believe that there has been a mistake during the tutorial slot assignment, please contact Karl Schrader immediately.

Image Processing and Computer Vision

Three Teaching Awards (2 in Computer Science, 1 in Mathematics)

Lecturer: Prof. Dr. Joachim Weickert

Assistant: Karl Schrader

Lectures (4h) with theoretical and programming assignments (2h);
(9 ETCS points)

Online lectures based on the Zoom platform: (privacy information):
Tuesday, 10:15-12:00
Friday, 10:15-12:00

First lecture: Tuesday, April 8
The Zoom link can be found in the Materials section.

Tutorials: 2 hours each week; see below.

Based on the maximum capacity of our tutorials, this lecture is limited to 192 participants.

Type of Lectures – Prerequisites – Tutorials – Registration – Written Exams – Contents – Literature

Type of Lectures

This class gives a broad introduction to the mathematically well-founded and model-based areas of image processing and computer vision. These fields are important in numerous applications including medical image analysis, computer-aided quality control, robotics, computer graphics, multimedia, data science, machine learning, and artificial intelligence. The class is required for starting a bachelor thesis in our group.

SInce this class also counts as a mathematics class, it does contain mathematics. Moreover, please note that it is mainly model-based.

Therefore, approaches relying on neural networks and deep learning only play a minor role (2 out of 30 lectures). Please consider alternative classes if this does not align with your specific interests.

It is planned that this class will be continued in the winter term by the class "Differential Equations in Image Processing and Computer Vision" which will bring you closer to our research topics. Both classes are required to pursue a master thesis in our group.

Prerequisites

This course is suitable for students of Visual Computing, Mathematics, Computer Science, Mathematics and Computer Science, Data Science and Artificial Intelligence, Bioinformatics, Mechatronics, and Physics.

It counts e.g. as a visual computing core area course within the Visual Computing program, and as a core course (Stammvorlesung) within Mathematics or Computer Science.

It is based on undergraduate mathematical knowledge from the first three semesters (such as "Mathematics for Computer Scientists I-III"). For the programming assignments, some elementary knowledge of C is required. The lectures are given in English.

Tutorials

The tutorials include homework assignments (theory and programming) as well as classroom assignments. The programming assignments give an intuition about the way how image processing and computer vision algorithms work, while the theoretical assigments provide additional mathematical insights. Classroom assignments are supposed to be easier and should guide you gently to the main themes.

For the homework assignments you can obtain up to 24 points per week. Actively participating in the classroom assignments gives you 12 more points per week, regardless of the correctness of your solutions. You can earn up to 2 bonus points in a tutorial by presenting a solution to a classroom assignment. To qualify for both exams you need 2/3 of all possible points. For 13 weeks, this comes down to 13 x 24 = 312 points. Working in groups of up to 3 people is permitted, but all persons must be in the same tutorial group.

If you miss a tutorial because you are sick, you can still get the points for participation, if you bring a doctor's certificate.

If you have questions concerning the tutorials, please do not hesitate to contact Karl Schrader.

Groups are scheduled for Tuesday and Wednesday:

Group 1: Tuesday, 12:15-14:00
Building E1.3, Seminar Room 015
Tutor: Ali El Chami
Group 2: Tuesday, 14:15-16:00
Building E1.3, Seminar Room 015
Tutor: Enes Ulus
Group 3: Tuesday, 14:15-16:00
Building E1.3, Seminar Room 014
Tutor: Vipil Vijay
Group 4: Tuesday, 16:15-18:00
Building E1.3, Seminar Room 015
Tutor: Tran Anh Dang Le
Group 5: Tuesday, 16:15-18:00
Building E1.3, Seminar Room 014
Tutor: Daniel Gaa
Group 6: Wednesday, 8:15-10:00
Building E1.1, Seminar Room 206
Tutor: Daniel Gaa

Registration

You have register for this course and enter your tutorial preferences via the CMS until 11.4.2024 12:00.

Please do not forget to register for the exam also in the HISPOS/LSF system (apart from Erasmus students). This system administrates your exam admission and your grades. It will allow registrations starting by the end of April.

Written Exams

There will be two written exams, one at the beginning and one at the end of the semester break.

The first written exam takes place on Wednesday, July 30, 14:00 - 17:00, in GHH (E2.2).

The second written exam takes place on Monday, September 22, 14:00 - 17:00, in GHH (E2.2).

Please be at the exam hall at 13:30 to allow for sufficient time for all organisational matters to be handled.

In order to qualify for the exams you need a total amount of 2/3 of all possible points from the homework and classroom assignments. In case of qualification, you are allowed to take part in both exams. The better grade counts, but each exam will count as an attempt individually. Exam admissions from previous semesters do not qualify you to take part in the exams of this course.

Both exams will be closed book exams. You will have to follow these rules:

You are allowed and obliged to bring three things to your desk only: Your student ID card (Studierendenausweis), a ball-pen that has no function other than writing, and a so-called cheat sheet. This cheat sheet is a A4 page with formulas or important equations from the lecture. Please note that the cheat sheet has to be handwritten by yourself. It will be collected at the end of the exam, and you can get it back at the exam inspection.
Everything else has to be deposited at the walls of the exam hall. In particular, electronic devices (including your cell phone), bags, jackets, briefcases, lecture notes, homework and classroom work solutions, additional handwritten notes, books, dictionaries, and paper are not allowed at your desk.
Please keep your student ID card ready for an attendance check during the exam.
Do not use pencils or pens that are erasable with a normal rubber.
You are not allowed to take anything with you that contains information about the exam.
A violation of this rule means failing the IPCV course.
You must stay until the exam is completely over.

If a student is unable to attend the written exams due to reasons beyond his/her control (e.g. because of an illness (medical certificate required immediately), or another exam at the same day), we aim to provide alternative options such as an online oral exam.

Course material is available on this webpage in order to support the teaching and the tutorials, not to replace them. Additional organisational information, examples and explanations that may be relevant for your understanding and the exam are provided in the lectures and tutorials. It is solely your responsibility - not ours - to make sure that you receive this information. Here is a preliminary list of the planned contents:

PART I: FOUNDATIONS AND TRANSFORMATIONS

Date	Topic
08.04.	Foundations I: Definitions, Image Types, Discretisation
11.04.	Foundations II: Degradations in Digital Images
15.04.	Foundations III: Colour Perception and Colour Spaces
17.04.	Image Transformations I: Continuous Fourier Transform (18:15-20:00)
22.04.	Image Transformations II: Sampling Theorem and Discrete Fourier Transform
25.04.	Image Transformations III: Discrete Cosine Transform and Image Pyramids
29.05.	Image Transformations IV: Discrete Wavelet Transform
02.05.	Image Compression
06.05.	Image Interpolation

PART II: IMAGE PROCESSING

Date	Topic
09.05.	Point Operations
13.05.	Linear Filters I: System Theory
16.05.	Linear Filters II: Derivative Filters
20.05.	Linear Filters III: Detection of Edges and Corners
23.05.	Nonlinear Filters I: Morphology and Median Filters
27.05.	Nonlinear Filters II: Wavelet Shrinkage, Bilateral Filters, NL-Means
30.05.	Nonlinear Filters III: Nonlinear Diffusion Filtering
03.06.	Global Filters I: Discrete Variational Methods
06.06.	Global Filters II: Continuous Variational Methods
10.06.	Global Filters III: Deconvolution Methods
13.06.	Texture Analysis

PART III: COMPUTER VISION AND IMAGE UNDERSTANDING

Date	Topic
17.06.	Image Sequence Analysis
20.06.	3-D Reconstruction I: Camera Geometry
24.06.	3-D Reconstruction II: Stereo
27.06.	3-D Reconstruction III: Shape-from-Shading
01.07.	Segmentation
04.07.	Object Recognition I: Hough Transform and Invariants
08.07.	Object Recognition II: Eigenspace Methods
11.07.	Object Recognition III: Neural Networks
15.07.	Object Recognition IV: Deep Learning
18.07.	Summary, Conclusions, Outlook

Literature

There is no specific text book for this class, but many of our image processing topics are covered in one of the following books:

J. Bigun: Vision with Direction. Springer, Berlin, 2010.
R. C. Gonzalez, R. E. Woods: Digital Image Processing. Addison-Wesley, International Edition, 2017.
K. D. Tönnies: Grundlagen der Bildverarbeitung. Pearson Studium, München, 2005.

Computer vision books include

R. Klette: Concise Computer Vision. Springer, London, 2014.
R. Szeliski: Computer Vision: Algorithms and Applications. Springer, New York, Second Edition, 2022.
E. Trucco, A. Verri: Introductory Techniques for 3-D Computer Vision. Prentice Hill, Upper Saddle River, 1998.

These and further books can be found in the mathematics and computer science library.
Furthermore, there is an interesting online compendium, where many researchers have written survey articles.
If you are looking for a specific reference, check out the Annotated Computer Vision Bibliography.
Many highly cited articles can be found via the Google Scholar webpage.