Computer Vision

Jump to: syllabus :: lectures


Course supervisor: Dipl.-Ing. Wanda Benešová, PhD
Supervising department: Institute of Applied Informatics (UAI FIIT)
Course objective: After completing the course, the students will have a theoretical background of digital image processing, they will be able to apply basic methods of digital image processing for solving of computer vision tasks of intermediate difficulty like image enhancement, segmentation, object recognition in the image and in movies. During the semester, students will work on a project using the computer vision library OpenCV from Intel.
Key words: digital image processing, machine vision
Form of teaching: lecture, seminar, project/semestral paper
Course methods: Form of study: lectures and exercises
Weekly: 2 hour lecture + 2 hour exercises
Time allowance (lecture/seminar): 2/3
Course completion: Mode of assessment and completing the course study: credit and examination
Mid-term assessment: midterm test in written form(10%)
Final assessment: final exam in written form (50%)
semester project (40%)
Mode of completion and credits: Exam (6 credits)
Type of study: usual
Taught for the form of: full-time, attendance method
Prerequisites for registration: none
Regular assessment: semester project (40%)
midterm test (10%)
Final assessment: final test (50%)


  1. Linear image filtration in spatial domain / image filtration in frequency domain
  2. Order filters, histogram based methods, image enhancement, image resampling
  3. Color, radiometry vs. photometry, CIE colorimetric system, multispectral imaging
  4. Image registration, panoramas, contour analysis, active contours
  5. Object segmentation, color segmentation, segmentation in videosequences
  6. Motion detection, optical flow, object tracking , Kalman filter
  7. Object detection, face detection, object and texture recognition, features detection, classification
  8. Local feature detectors and descriptors (SIFT, SURF, MSER, BRIEF…)
  9. Image alignment, image registration and RANSAC
  10. Object recognition, Bag-of-words models
  11. Stereo, imaging in 3D

OpenCv in Exercises