Course detail

Machine Vision

FSI-VSV-A Acad. year: 2025/2026 Summer semester

Supervisor

doc. Ing. Pavel Škrabánek, Ph.D.

Department

Institute of Automation and Computer Science

Learning outcomes of the course unit

Prerequisites

Planned learning activities and teaching methods

Assesment methods and criteria linked to learning outcomes

Knowledge and skills are verified by credit and examination. Credit requirements: elaboration of a given practical task. Attendance at lectures is recommended, while attendance at practical sessions is mandatory. Practical sessions that a student is unable to attend in the regular term can be made up during a substitute term. The exam is oral and covers the entire course material.

Language of instruction

English

Aims

To acquaint students with basic principles of interaction of radiation with matter, with instrumentation for applications of computer vision in industry, and with image processing methods used in machine vision applications.

At the end of the course, the students will be able to:

  • select appropriate instrumentation for various machine vision applications,
  • design appropriate installation of the instrumentation,
  • create data processing parts of machine vision systems for basic machine vision applications.

Specification of controlled education, way of implementation and compensation for absences

The study programmes with the given course

Programme N-AIŘ-P: Applied Computer Science and Control, Master's
branch ---: no specialisation, 5 credits, compulsory

Type of course unit

 

Lecture

26 hours, optionally

Syllabus


  1. Introduction, interaction of radiation with matter, formation of images, parts of computer vision systems for industrial applications, typical applications of machine vision.

  2. Lighting geometry and its effect on the final image, radiation sources for machine vision, lighting in the visible, infrared and ultraviolet spectrums.

  3. Lenses with perspective projection – focal length, aperture and basic concepts related to perspective projection, intermediate rings, depth of field, lens defects and their compensation, lens resolution, telecentric lenses.

  4. Photodiode, CMOS sensors, electronic shutters, quantum efficiency of image sensors, formation of digital images, camera electronic circuits and their impact on noise in images.

  5. Optical filters and their use in machine vision, multispectral imaging, instrumentation for machine vision (line and area-scan digital cameras, light sources, optical filters, lenses).

  6. Design of the instrumentation part of a machine vision system (task processing, data collection and evaluation, documentation).

  7. Image histogram, intensity scale transformation, geometric transformations, interpolation.

  8. Introduction to spatial domain filtering, restoration of noise-affected images, edge detection.

  9. Image segmentation.

  10. Morphological transformations and their applications in image processing.

  11. Evaluation of processed images (shape detection, blob detection, measurement of distances and angles).

  12. Image classification.

  13. Object detection in images

Laboratory exercise

26 hours, compulsory

Syllabus


  • Introduction to the subject matter, laboratory safety procedures

  • Installation and operation of illuminators, lens Installation and adjustment, working with optical filters

  • Connection and configuration of industrial cameras

  • Software for design and implementation of image processing pipelines

  • Design and implementation of a computer vision system for a given task