Computer Vision - Image Understanding - Bildverstehen
Exam SS 2018
The grades have been sent to the administration. You can have a look at your work during my speaking hours (Mondays between 13:00 and 14:00) when I am back from holidays, i.e. after September 17th.
Prerequisites: Modules in Mathematics I to IV, basic knowledge in Python.
Exam: written examination (90 minutes), 5 credit points.
Contact: julien dot vitay at informatik dot tu-chemnitz dot de.
Language: English. The written exam can of course be done in German.
The course is an introduction to computer vision, from basic image processing (filters, Fourier transformation) to more advanced algorithms (object recognition, movement, facial features extraction).
- Image formation
- Image processing
- Geometric transformations
- Feature detection and matching
- Motion, optical flow
The exercises are made on computers using the OpenCV computer vision library with the Python bindings.
The course is based primarily on the textbook by Richard Szeliski:
Richard Szeliski (2010). Computer Vision: Algorithms and Applications. Springer.
A free online draft is available at szeliski.org/Book/
The online book by Simon Prince, Computer vision: models, learning and inference (available at computervisionmodels.com) might also be helpful.
Slides for the lecturesChapter 01 - Introduction (pdf)
Chapter 02 - Image Formation (pdf)
Chapter 03 - Image processing (pdf)
Chapter 04 - Geometric transformations (pdf)
Chapter 05 - Feature detection and matching (pdf)
Chapter 06 - Segmentation (pdf)
Chapter 07 - Motion (pdf)
Chapter 08 - Stereovision (pdf)
ExercisesExercise 01 - Introduction to Python and NumPy. (pdf , data , solution )
Exercise 02 - Basic image processing. (pdf , data , solution )
Exercise 03 - Linear Filtering. (pdf , solution )
Exercise 04 - Edge detection. (pdf , data , solution )
Exercise 05 - Fourier transforms. (pdf , data , solution )
Exercise 06 - Face Swapping (cancelled). (pdf , data , solution )
Exercise 07 - Feature detection and matching. (pdf , data , solution )