|
Lecturer(s)
|
-
Mautner Pavel, Ing. Ph.D.
|
|
Course content
|
1. Computer vision and basic characteristics, mathematical model of image, image pre-processing, segmentation, recognition, reconstruction (3D), image capturing, analogue to digital conversion (ADC, sampling and quantizing). 2. Image properties, connectivity, neighbourhood, distance, path, connected set of pixels, boundary and boundary extraction, curves and lines on a discrete grid, shape representation, area and perimeter, moments and centre-point of region, eccentricity. 3. Histograms, grey-level transformation, monadic and dyadic operators, image addition, subtraction and multiplication, histogram stretching, shrinking, slide, equalization and specification. 4. Image segmentation, thresholding, automatic thresh detection, transformed histograms, scatter plots, grey-level co-occurrence matrix. 5. Image segmentation, region based segmentation technique, region growing, region operations and detection, region splitting and merging. 6. Image filtration and high-pass filters, edge detection, vertical and horizontal edge, gradient operators (Roberts, Prewitt, Sobel), compass operators, Laplace operator, line and spot detection, image sharpening. 7. Image filtration and low-pass filters, linear and nonlinear digital filtration, noise, signal processing vs. IIR and FIR filter, some characteristics of filtering methods. 8. Mathematical morphology, point set, structuring element, basic morphological operations, erosion, dilation, opening and closing operations, hit and miss transform, thinning and thickening. 9. Thinning and skeleton, medial axis transform, classical thinning algorithm, multiple pixels method of thinning, thinning and skeleton algorithms in the context of the morphological operations. 10.Image representation in the frequency domain, the properties of the two-dimensional Fourier transform, DFT-Discrete Fourier Transform, digital filtration. 11. Chain code for boundaries representation, Freeman?s chain code, differential chain code, Fourier descriptors for shape representation, Run-Length Codes (RLC). 12. Standards of image data format, compression of image. 13. Introduction to pattern recognition, general pattern recognition problem, objects classification.
|
|
Learning activities and teaching methods
|
Interactive lecture, One-to-One tutorial, Seminar classes
- Preparation for comprehensive test (10-40)
- 20 hours per semester
- Preparation for an examination (30-60)
- 30 hours per semester
- Contact hours
- 65 hours per semester
- Graduate study programme term essay (40-50)
- 45 hours per semester
|
| prerequisite |
|---|
| Knowledge |
|---|
| program at the level of subjects KIV / PPA1, KIV / PPA2 and KIV / PT, eg programming languages Java, C / C ++, C # |
| apply methods of probability calculus and statistics and numerical mathematics in the range of subjects KMA / PSA and KMA / NM |
| analyze and process signals in the scope of the subject KIV / AZS |
| Skills |
|---|
| use programming techniques and data structures and algorithmize tasks |
| solve probability calculus problems and statistics, algorithmize numerical mathematics problems |
| use basic signal processing techniques, ADC, FIR, IIR, DFT issues |
| Competences |
|---|
| N/A |
| N/A |
| N/A |
| learning outcomes |
|---|
| Knowledge |
|---|
| understand the principles of machine vision, description, topology and geometry of the image scene |
| be familiar with the principles and methods of image filtering in the spatial and frequency domains |
| využívat vlastností histogramu pro segmentaci prahováním a jasové transformace |
| apply morphological transformations |
| perform skeletization and thinning of objects in the image |
| Skills |
|---|
| implement image filtering in the spatial and frequency domains |
| perform luminance transformations, e.g. histogram equalization etc. |
| detect the boundaries of objects in the image |
| segment images by thresholding or area spacing methods |
| define the skeleton of the object and implement algorithms for dilation and erosion of objects |
| Competences |
|---|
| N/A |
| N/A |
| teaching methods |
|---|
| Knowledge |
|---|
| Interactive lecture |
| One-to-One tutorial |
| Seminar classes |
| Self-study of literature |
| Skills |
|---|
| Interactive lecture |
| Seminar classes |
| Individual study |
| One-to-One tutorial |
| Competences |
|---|
| Interactive lecture |
| Seminar classes |
| One-to-One tutorial |
| Individual study |
| assessment methods |
|---|
| Knowledge |
|---|
| Test |
| Seminar work |
| Combined exam |
| Skills |
|---|
| Test |
| Seminar work |
| Individual presentation at a seminar |
| Combined exam |
| Competences |
|---|
| Individual presentation at a seminar |
| Seminar work |
| Combined exam |
|
Recommended literature
|
-
Dobeš, Michal. Zpracování obrazu a algoritmy v C#. 1. vyd. Praha : BEN - technická literatura, 2008. ISBN 978-80-7300-233-6.
-
Hlaváč, Václav; Sedláček, Miloš. Zpracování signálů a obrazů. 1. vyd, dotisk. Praha : Vydavatelství ČVUT, 2001. ISBN 80-01-02114-9.
-
Sonka, Milan; Boyle, Roger; Hlavac, Vaclav. Image processing, analysis, and machine vision. 2nd ed. Pacific Grove : PWS Publishing, 1999. ISBN 0-534-95393-X.
-
Šonka, Milan; Hlaváč, Václav. Počítačové vidění. Praha : Grada, 1992. ISBN 80-85424-67-3.
-
Umbaugh, Scott E. Computer imaging : digital image analysis and processing. Boca Raton : Taylor & Francis, 2005. ISBN 0-8493-2919-1.
-
Umbaugh, Scott E. Digital Image Processing and Analysis: Applications with MATLAB and CVIPtools. Boca Raton : Taylor & Francis, 2018. ISBN 978-1-4987-6602-9.
|