de | en

Image Understanding I: Machine Vision Algorithms

Module IN2023

This Module is offered by TUM Department of Informatics.

This module handbook serves to describe contents, learning outcome, methods and examination type as well as linking to current dates for courses and module examination in the respective sections.

Basic Information

IN2023 is a semester module in German language at Master’s level which is offered in summer semester.

This Module is included in the following catalogues within the study programs in physics.

  • Catalogue of non-physics elective courses
Total workloadContact hoursCredits (ECTS)
90 h 30 h 3 CP

Content, Learning Outcome and Preconditions

Content

The lecture provides a detailed description of methods and algorithms that are relevant in practice for solving industrial vision applications. The selection of methods is based on the most important application domains of image processing in industry: positioning/alignment, metrology, and object recognition. The main focus of the lecture is the description of the methods and their basic principles. Practical examples show the typical applications in which the presented methods are used. In detail, the following topics are covered:
- Image acquisition
- Image enhancement
- Segmentation and feature extraction
- Morphology
- Edge extraction
- Segmentation and fitting of geometric primitives
- Camera calibration
- Template matching

Learning Outcome

Participants of this lecture will have a thorough understanding of the essential hardware components of a machine vision system as well as the theory, data structures, and implementation of the most important machine vision algorithms. They are capable of analyzing and evaluating machine vision tasks and can use their knowledge and skills to create machine vision applications.

Preconditions

The lecture requires basic knowledge of the following fields: linear algebra (linear transformations between vector spaces expressed in matrix algebra), calculus (in particular, sums and differentiation and integration of one- and two-dimensional functions).

Courses, Learning and Teaching Methods and Literature

Courses and Schedule

TypeSWSTitleLecturer(s)Dates
VO 2 Image Understanding I: Machine Vision Algorithms (IN2023) Fri, 08:30–10:00, Interims I 102

Learning and Teaching Methods

Lecture (presentation of slides and interactive examples)

Media

PowerPoint

Literature

Carsten Steger, Markus Ulrich, Christian Wiedemann: Machine Vision Algorithms and Applications; Wiley-VCH, Weinheim, 2007

Module Exam

Description of exams and course work

The exam takes the form of a 60 minutes written test. Application questions assess the ability to analyze, evaluate, and create realistic machine vision applications. Knowledge questions assess the acquaintance with the hardware components and algorithms of machine vision as well as the suitability of the choice of hardware components and algorithms to solve a particular application.

Exam Repetition

The exam may be repeated at the end of the semester.

Top of page