Machine Vision Systems

Course Description

Machine vision systems are commonly used in manufacturing for visual process control and visual inspection. The most critical part of any machine vision system is image acquisition as low-quality images make process control and visual inspection impossible.
In this course the student will primarily acquire the knowledge about the image acquisition part of a machine vision system.
The following topics are covered: Introduction to machine vision. Image acquisition and processing chain. Illumination. Interaction between light and object's surface. Bidirectional reflectance distribution function. Lambertian reflectance. Light sources. Spatial arrangement of illumination. Lightfield and darkfield. Background illumination. Diffuse illumination. Lenses. Focal length. Focal plane. Aperture. Field of view. Depth of field. F-number. Mounts. Lens types. Optical sensor types. Mechanical and electronic shutter. Integration time. Global and rolling shutter. Progressive and interlaced scanning. Optical transfer function. Modulation transfer function. Resolution of lens-sensor pair. Paring a lens with a sensor. Image formation model. Radial distortion (pincushion and barrel). Perspective and orthographic projection. Geometric camera calibration. Camera to computer interfaces. Industrial standards: GenICam, GigEVision, USB3Vision, CameraLink. Color. Optical filters. Bayer filter. Demosaicing. RGB and YUV images. Image registration. Geometrical transformations. Homography. Processing paradigm: acquire-register-analyze. Examples from industry: visual quality control. Software tools: OpenCV.

Learning Outcomes

  1. define the basic concepts of machine vision
  2. list standards and technologies which are used in machine vision
  3. select which illumination to use depending on the application
  4. select which camera to use depending on the application
  5. compute parameters of illumination and of lens for good image acquisition
  6. develop a machine vision system for visual quality control

Forms of Teaching

Lectures

Lectures present theoretical concepts that are illustrated using concrete examples.

Laboratory

Laboratory exercises introduce the student to the standard machine vision hardware.

Grading Method

Continuous Assessment Exam
Type Threshold Percent of Grade Threshold Percent of Grade
Laboratory Exercises 50 % 20 % 50 % 20 %
Seminar/Project 20 % 20 % 20 % 20 %
Mid Term Exam: Written 20 % 30 % 0 %
Final Exam: Written 20 % 30 %
Exam: Written 50 % 60 %
Comment:

The threshold on the combined midterm and final exam score is 50%.

Week by Week Schedule

  1. Introduction to machine vision. Image acquisition and processing chain.
  2. Illumination. Interaction between light and object's surface. Bidirectional reflectance distribution function. Lambertian reflectance.
  3. Light sources. Spatial arrangement of illumination. Lightfield and darkfield. Background illumination. Diffuse illumination.
  4. Lenses. Focal length. Focal plane. Aperture. Field of view. Depth of field. F-number. Mounts. Lens types.
  5. Optical sensor types. Mechanical and electronic shutter. Integration time. Global and rolling shutter. Progressive and interlaced scanning.
  6. Optical transfer function. Modulation transfer function. Resolution of lens-sensor pair. Paring a lens with a sensor.
  7. Image formation model. Radial distortion (pincushion and barrel). Perspective and orthographic projection.
  8. Midterm exam
  9. Geometric camera calibration.
  10. Camera to computer interfaces. Industrial standards: GenICam, GigEVision, USB3Vision, CameraLink.
  11. Color. Optical filters. Bayer filter. Demosaicing. RGB and YUV images.
  12. Image registration. Geometrical transformations. Homography.
  13. Processing paradigm: acquire-register-analyze. Examples from industry: visual quality control.
  14. Presentation of students' projects
  15. Final exam

Study Programmes

University graduate
[FER3-HR] Audio Technologies and Electroacoustics - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Communication and Space Technologies - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Computational Modelling in Engineering - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Computer Engineering - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Computer Science - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Control Systems and Robotics - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Data Science - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Electrical Power Engineering - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Electric Machines, Drives and Automation - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Electronic and Computer Engineering - profile
Elective Courses (1. semester) (3. semester)
Elective Courses of the Profile (1. semester) (3. semester)
[FER3-HR] Electronics - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Information and Communication Engineering - profile
Elective Courses (1. semester) (3. semester)
Elective Courses of the Profile (1. semester)
Elective Coursesof the Profile (3. semester)
[FER3-HR] Network Science - profile
Elective Courses (1. semester) (3. semester)
[FER3-HR] Software Engineering and Information Systems - profile
Elective Courses (1. semester) (3. semester)

Literature

Alexander Hornberg, editor (2006.), Handbook of Machine Vision, Willey-VCH
Sidney F. Ray (2002.), Applied Photographic Optics, Focal Press
E. R. Davies (2004.), Machine Vision: Theory, Algorithms, Practicalities, Morgan Kaufmann

For students

General

ID 222790
  Winter semester
5 ECTS
L0 English Level
L1 e-Learning
30 Lectures
0 Seminar
0 Exercises
15 Laboratory exercises
0 Project laboratory

Grading System

87 Excellent
75 Very Good
63 Good
51 Sufficient

Similar Courses