Objectives and competences
The aim of this course is that students will understand the theoretical basics of the computer based machine vision, be able to analyze individual parts of machine vision algorithms and solve the complex problems of machine vision in industry environment.
Content (Syllabus outline)
• Computer and machine image capturing and processing systems.
• Colour systems, human vision system (HVS).
• Digital image processing fundamentals and algorithms (image enhancement, edge and boundary detection, skeletonization, merging and splitting regions, morphological operations and linear transformations).
• Pattern and images recognition fundamentals and algorithms (future extraction, parameters estimations, supervision and non-supervision learning).
• Scene analysis (target and shape recognition in time and frequency domain, image futures and descriptions).
• Neural networks and fuzzy logic in pattern recognition.
• Machine vision applications: quality control, vision controlled robots, vision navigated autonomous vehicles, traffic control, distance measurements, stereo vision, orientation estimation.
• Object detection and recognition, face recognition, data mining.
• Processing of radar data: synthetic aperture radar and georadar data.
Learning and teaching methods
• lectures,
• tutorial,
• project based lab work.
Intended learning outcomes - knowledge and understanding
On completion of this course the student will be able to
• explain, understand, develop, design and realize computer vision systems,
• pattern recognition using camera with basics algorithms,
• analysis,
• design machine vision systems in practical applications.
Intended learning outcomes - transferable/key skills and other attributes
Communication skills: oral lab work defence, manner of expression at written examination.
Use of information technology: use of computer vision software tools.
Calculation skills: performing calculation operations in computer vision systems.
Problem solving: designing and implementing of simple machine vision systems.
Readings
• N. Pavešič: Razpoznavanje vzorcev, uvod v analizo in razumevanje vidnih in slušnih signalov, 2. razširjena izdaja, Fakulteta za elektrotehniko, Ljubljana, 2000.
• Forsyth, D.A. and Ponce, J., Computer Vision: A Modern Approach, 2nd edition 2011.
• P. Azad, T. Gockel, R. Dillman, Computer Vision: Principles and Practice, Elektor, 2008.
• Richard Szeliski, Computer Vision: Algorithms and Applications. Springer-Verlag, 2010.
Prerequisits
Basics of signals theory and basics of computer programming.
Additional information on implementation and assessment The written exam may be substituted with continuous knowledge testing and assessment.
