UIN3027 Image Analysis and Recognition

Faculty of Philosophy and Science in Opava
Winter 2023
Extent and Intensity
2/2/0. 6 credit(s). Type of Completion: zk (examination).
Teacher(s)
Ing. Jiří Blahuta, Ph.D. (lecturer)
RNDr. Jiří Martinů, Ph.D. (seminar tutor)
Guaranteed by
Ing. Jiří Blahuta, Ph.D.
Institute of Computer Science – Faculty of Philosophy and Science in Opava
Timetable
Mon 11:25–13:00 LEI
  • Timetable of Seminar Groups:
UIN3027/A: Wed 15:35–17:10 LEI, J. Martinů
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
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
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
Czech
Further comments (probably available only in Czech)
Study Materials
The course can also be completed outside the examination period.
Teacher's information
Scope of the course: The IR course deals with the digital image processing. The first chapters deal with ways of taking the digital image and its discrete representation. The pivotal chapters are aimed at the individual phases of the image processing - from pre-processing, filtrations to the segmentation problems and the understanding of the image content using classifiers with feature analysis of segmented data. In seminars, students will get acquainted with HW processor modules with illustrative examples, which can be found in the text at the end of the chapter in the study materials. 1. Introduction to the Image Recognition, Terms 2. Bitmap and Vector Images 3. Image Scanning and the Digital Image Concept 4. Image Pre-Processing / Histogram, Filtrations, Noise/ 5. ROI Detection, Examples 6. Image Segmentation. Binary Thresholding 7. Seed Algorithm, Region Growing Method 8. Object Description After Segmentation 9. Understanding the Image Content, Classifiers 10. Classification According to Etalons 11. Classifiers as Artificial Neural Networks 12. Application of the Recognized Image 13. Revision course Terms of abs. * 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%
The course is also listed under the following terms Winter 1993, Winter 1994, Winter 1995, Winter 1996, Winter 1997, Winter 1998, Winter 1999, Winter 2000, Winter 2001, Winter 2002, Winter 2003, Winter 2004, Winter 2005, Winter 2006, Winter 2007, Winter 2008, Winter 2009, Winter 2010, Winter 2011, Winter 2012, Winter 2013, Winter 2014, Winter 2015, Winter 2016, Winter 2017, Winter 2018, Winter 2019, Winter 2020, Winter 2021, Winter 2022, Winter 2024.
  • Enrolment Statistics (Winter 2023, recent)
  • Permalink: https://is.slu.cz/course/fpf/winter2023/UIN3027