Course: Machine Vision

» List of faculties » FM » ITE
Course title Machine Vision
Course code ITE/PVI
Organizational form of instruction Lecture + Lesson
Level of course Master
Year of study not specified
Semester Winter
Number of ECTS credits 5
Language of instruction Czech, English
Status of course Compulsory, Compulsory-optional
Form of instruction Face-to-face
Work placements Course does not contain work placement
Recommended optional programme components None
Lecturer(s)
  • Paleček Karel, Ing. Ph.D.
  • Chaloupka Josef, doc. Ing. Ph.D.
Course content
Content of lectures and exercises: 1. Image signal processing, image acquisition, radiometry, optical part of the camera, CCD and CMOS sensors, colour spaces, geometric transformations. 2. Pixel brightness transformations, linear discrete image transforms, 2D FFT and DCT, Hadamard transform, Wavelets, discrete linear integral transformation, use of LDT in image processing. 3. Image smoothing, edge detectors - convolution masks approximating the derivative of the image function. 4. Image segmentation, thresholding, automatic threshold finding, edge exploitation, graph exploitation. 5. Image segmentation 2, advanced methods using deeper image analysis, region coloring, image moments, simple recognition features, region, compactness, chain codes. 6. Finding parametrically describable objects, Hough transform, RANSAC method. 7. Object detection and tracking, use of simple operators, Laplace, Harris corner detector, Shi-Tomasi corner detector, other fast algorithms for finding corners. 8. Features for objects describing, SIFT (Scale-Invariant Feature Transform), SURF (Speeded-Up Robust Features), BRIEF (Binary Robust Independent Elementary Features). 9. Image comparison (matching) based on the use of image features. 10. Introduction to 3D image reconstruction. 11. Video analysis, object tracking, CamShift algorithm, MeanShift algorithm, KLT algorithm, use of optical flow, background separation. 12. Automatic video segmentation, segmentation algorithms. 13. Simple classifiers for image recognition, PCA (Principal Component Analysis), use of SVM (Support Vector Machines), AdaBoost algorithm, Viola-Jones detector. 14. Artificial neural networks in image recognition, theory and practical applications. Convolutional neural networks (CNN) and recurrent neural networks for image recognition.

Learning activities and teaching methods
Monological explanation (lecture, presentation,briefing)
  • Class attendance - 56 hours per semester
Learning outcomes
The subject Machine Vision is focused on student's ability to understand basic principles of computer image processing and recognition.
Theoretic piece of knowledge and practical skills from requered areas
Prerequisites
unspecified

Assessment methods and criteria
Written exam

Requirements for getting a credit are activity at the seminars. Examination is of the written forms.
Recommended literature
  • DAVIES, E., R.. Computer and Machine Vision, Fourth Edition: Theory, Algorithms, Practicalities.. UK, 2012. ISBN 978-0123869081.
  • HLAVÁČ, Václav a Miloš SEDLÁČEK. Zpracování signálů a obrazů. 2. přeprac. vyd.. ČR, 2007. ISBN 978-80-01-03110-0.
  • CHALOUPKA, J. Přednášky, cvičení - PVI.
  • Raschka, S., Liu, Y., Mirjalili, V., Dzhulgakov, D. Machine Learning with PyTorch and Scikit-Learn: Develop machine learning and deep learning models with Python. In Packt Publishing, 2022. ISBN 978-1801819312.
  • ŠONKA, Milan, Václav HLAVÁČ a Roger BOYLE. Image processing, analysis, and machine vision. 3rd ed.. Toronto: Thomson, 2008. ISBN 978-0-495-08252-1.
  • Ying Liu. Deep Learning Based Image Processing: Recent Advances and Future Trends. In Eliva Press, 2022. ISBN 978-9994982554.


Study plans that include the course
Faculty Study plan (Version) Category of Branch/Specialization Recommended year of study Recommended semester
Faculty: Faculty of Mechatronics, Informatics and Interdisciplinary Studies Study plan (Version): Automatic Control and Applied Computer Science (2016) Category: Special and interdisciplinary fields 2 Recommended year of study:2, Recommended semester: Winter
Faculty: Faculty of Mechatronics, Informatics and Interdisciplinary Studies Study plan (Version): Mechatronics (2016) Category: Special and interdisciplinary fields 2 Recommended year of study:2, Recommended semester: Winter
Faculty: Faculty of Mechatronics, Informatics and Interdisciplinary Studies Study plan (Version): Information Technology (2013) Category: Informatics courses 2 Recommended year of study:2, Recommended semester: Winter