Computer Vision - Image Understanding
|Vorlesung:||Freitag,||11.30 - 13.00, 1/346,||(Dr. J. Vitay)|
|Übung:||Dienstag,||17.15 - 18.45, 1/B202,||(Dr. J. Vitay)|
|Übung:||Donnerstag,||17.15 - 18.45, 1/B202,||(Dr. J. Vitay)|
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.
Start of the winter semester: The first lecture will be on Friday 14.10 at 11:30. The exercises only start on 18.10 and 20.10 at 17:15 in B202.
If you also follow the Machine Learning course, the two first weeks of exercise will be common to the two courses: the first week is an introduction to Python, the second an introduction to Numpy and Matplotlib. You only need to do them once.
The course will be an introduction to computer vision, from basic image processing (filters, Fourier transformation) to more advanced algorithms (object recognition, movement, facial features extraction).
- Local Operations
- Global operations
- Affine transformations
- Contours / Segmentation
- Motion, optical flow
- Feature detection
- Machine learning techniques
- Active appearance models
The exercises will be 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.