FPF:UINA327 Image Analysis and Recognition - Course Information
UINA327 Image Analysis and Recognition
Faculty of Philosophy and Science in OpavaWinter 2020
- Extent and Intensity
- 2/2/0. 6 credit(s). Type of Completion: zk (examination).
- Teacher(s)
- doc. Ing. Petr Čermák, Ph.D. (lecturer)
doc. Ing. Petr Čermák, Ph.D. (seminar tutor) - Guaranteed by
- doc. Ing. Petr Čermák, Ph.D.
Institute of Computer Science – Faculty of Philosophy and Science in Opava - Prerequisites (in Czech)
- TYP_STUDIA(N)
- Course Enrolment Limitations
- The course is also offered to the students of the fields other than those the course is directly associated with.
- fields of study / plans the course is directly associated with
- Computer Science and Technology (programme FPF, N1801 Inf)
- Computer Science (programme FPF, CompSci-np)
- Course objectives
- The course called Image Analysis and Recognition is focused on digital image processing, objects classification of the digital image and understanding of the digital images. The first part of the course is devoted to ways of digital image acquisition and its digital representation. Principal chapters are focused on all phases of image processing - from pre-processing, filtration to segmentation followed by understanding by means of classifiers with feature-based analysis of the segmented image data.
- Syllabus
- 1. Mathematical description of continuous and digital image, physiological and psychological aspects of vision
2. Mathematical model of gray-scale and color vision, image types and devices for their acquisition
3. Linear operators, image adding and convolution, cyclic convolution, boundary conditions
4. Sampling, aliasing, antialias filtering, image reconstruction, examples of reconstruction filters
5. Numerical noise filtering, image sharpening and edge sharpening, fuzzy filtration, histogram and its equalization
6. Image segmentation by binary thresholding and adaptive thresholding, boundary tracking, segmentation by Region Growing and Region Splitting and Merging, segmentation by pattern matching, segmentation by fuzzy rule-based system
7. Mathematical and fuzzy mathematical morphology, homotopic tree, skeletonization, dilation, erosion, opening
8. Hough transform, line approximation and approximation of circle
9. Features detection, global and local features, features from pixel intensity, boundary description, Euler´s number, texture-based features, polygonal representation
10. Regions and their description, regions indexing, scalar description, moments, features evaluation, independency towards image transforms
11. Pattern recognition, statistical feature-based methods, classifiers settings, clustering, recognition by etalons, neuro and fuzzy-neuro classifiers
- 1. Mathematical description of continuous and digital image, physiological and psychological aspects of vision
- Literature
- required literature
- SOJKA, E. Zpracování digitálního obrazu. 2000. ISBN 80-7078-746-5. info
- recommended literature
- SZELISKI, Richard. Computer Vision: Algorithms and Applications. Berlin, 2010. info
- DOUGHERTY, G. Digital Image Processing for Medical Applications. Oxford, 2009. ISBN 978-0521860857. info
- ŽÁRA, Jiří, SOCHOR, Jiří, FELKEL, Petr, BENEŠ, Bedřich. Moderní počítačová grafika. Brno, 2005. ISBN 978-80-2510-454-5. info
- SCHLESINGER, M.I., HLAVÁČ, V. Deset přednášek z teorie statistického a strukturního rozpoznávání. Praha, 1999. info
- ŠONKA, M., HLAVÁČ, V., BOYLE, R. Image Processing, Analysis and Machine Vision. Boston, 1998. info
- HARALICK, R. M. , SHAPIRO, L. G. Computer and Robot Vision. New York, 1992. info
- PRATT, W. K. Digital Image Processing, Second Edition. New York, 1991. info
- Teaching methods
- Interactive lecture
Lecture with a video analysis - Assessment methods
- Exam
- Language of instruction
- English
- Further comments (probably available only in Czech)
- The course can also be completed outside the examination period.
- Teacher's information
- * 75% attendance in the lecture and exercises, active participation
* written test in the extent of the given literature and the content of seminars - success rate 50% of 30 points
* implementation of selected methods of image analysis on selected robot, success rate 50% of 30 points from programming and 10 points from documentation
* 40 points exam, sucess rate 50%
- Enrolment Statistics (Winter 2020, recent)
- Permalink: https://is.slu.cz/course/fpf/winter2020/UINA327