|
Lecturer(s)
|
-
Bischoff Stefan, prof. RNDr.
|
|
Course content
|
The main topics are: - Image acquisition and representation - Preprocessing methods: transformations of pixel brightness and geometry, camera calibration, local operators - Video and audio compression - Image segmentation: thresholding, edge-based and region-based segmentation, Hough transformation, template matching, motion segmentation, optical flow - Feature extraction: color, texture and shape descriptors; Principal Component Analysis (PCA) - Classification: prototypes, cluster analysis, statistical methods, classifiers - Teachable image evaluation: supervised and non-supervised learning, neural networks, Support-Vector-Machines (SVM) - Multi-sensor technology: depth sensors, photogrammetry, 3D scene reconstruction Overview of current practical application areas: visual quality inspection, robotics, medical diagnosis, video conference systems, biometry, security
|
|
Learning activities and teaching methods
|
Lecture, Practicum
- Home preparation for classes
- 34 hours per semester
- Preparation for credit
- 10 hours per semester
- Preparation for exam
- 50 hours per semester
- Class attendance
- 56 hours per semester
|
|
Learning outcomes
|
This course provides a general introduction to the fundamental techniques of computer vision and image processing and illustrates their practical application.
Graduates from this course will obtain good knowledge of the field of image processing
|
|
Prerequisites
|
Knowledge in C/C++ (Delphi is not sufficient)
|
|
Assessment methods and criteria
|
Combined examination
Requirements for getting a credit are activity at the practicals /seminars. Examination is of the writing and oral forms.
|
|
Recommended literature
|
-
Bernd Jähne and Horst Haußecker. Computer Vision and Applications, A Guide for Students and Practitioners. Academic Press, 2000. ISBN 0-13-085198-1.
-
Bernd Jähne. Digital Image Processing. Springer, 2002. ISBN 3540677542.
-
David A. Forsyth and Jean Ponce. Computer Vision, A Modern Approach. Prentice Hall, 2003. ISBN 0-12-379777-2.
-
E. R. Davies. Machine Vision : Theory, Algorithms, Practicalities. Morgan Kaufmann, 2005. ISBN 0-12-206093-8.
-
Gary Bradski and Adrian Kaehler. Learning OpenCV - Computer Vision with the OpenCV Library. O'Reilly Media Inc., 2008. ISBN 978-0-596-51613-0.
|