Informationen für
Logo VIS

« Zurück

Computer Vision (in Englisch)
Typ: Hauptstudium / Vertiefungslinie
Semester: WS 2013/2014
Umfang: 3V+1Ü
Studiengang: Diplom Informatik, Diplom Softwaretechnik, Master Informatik, Master Softwaretechnik
Dozent: Prof. Dr.-Ing. Andrés Bruhn

This class gives an in-depth introduction into the field of computer vision. It consists of four parts. In the first part, characteristic image features and feature descriptors are discussed that are typically used for recognition or matching, The second part of the course is dedicated to motion and stereo. Fundamental goals in this context are the recovery of the 3-D structure and the 2-D motion of objects from a recorded scene. The third part of the class is dedicated to segmentation - the subdivision of an image into different semantically meaningful regions. Here, the focus lies on contour based methods that are among the leading techniques in the field. Finally, the fourth part deals with pattern recognition the classification of features into different groups. In this context, basic approaches for the reducing the dimensionality of features and strategies for supervised learning are discussed.

This class requires undergraduate knowledge in mathematics (e.g. ''Mathematik für Informatiker und Softwaretechniker", "Numerische und stochastische Grundlagen der Informatik"). The previous attendance of the class "Imaging Science" is recommended. Lectures will be in English.

This class is particularly useful for those students who wish to pursue a bachelor, master or diploma thesis in our group.



    The replacement lecture will take place on Friday, November 8th, 15:45-17:15 in Lecture Hall V38.04.
    Since the introduction of the institutes to the Master students (Ringvorlesung) will take place in Lecture Hall V38.02, there will be no lecture.
    Due to constructions the first lecture is moved to Lecture Hall V4.01 in Building 4 (see map)
    The time slots for the lecture and the tutorials have been interchanged.
    The first lecture will be on Thursday,  October 17th.



Lecture Notes:

PART 1 : Features and Descriptors

  1. Introduction (Update) (17.10.2013)
  2. Features and Descriptors I: Linear Diffusion, Scale Space (18.10.2013)
  3. Features and Descriptors II: Image Pyramids, Edges and Corners (24.10.2013)
  4. Features and Descriptors III: Hough Transform, Invariants (31.10.2013)
  5. Features and Descriptors IV: Texture Analysis (08.11.2013)
  6. Features and Descriptors V: Scale Invariant Feature Transform (08.11.2013)

PART 2 : Motion and Stereo

  1. Image Sequence Analysis I: Local Methods (14.11.2013)
  2. Image Sequence Analysis II: Motion Models, Tracking, Feature Matching (15.11.2013)
  3. Image Sequence Analysis III: Variational Methods (22.11.2013)
  4. 3-D Reconstruction I: Camera Geometry (28.11.2013)
  5. 3-D Reconstruction II: Epipolar Geometry, Stereo Matching (29.11.2013)
  6. 3-D Reconstruction III: Shape-from-Shading (06.12.2013)

PART 3 : Segmentation

  1. Foundations I: Isotropic Nonlinear Diffusion (12.12.2013)
  2. Foundations II: Anisotropic Nonlinear Diffusion (13.12.2013)
  3. Segmentation I: The Mumford/Shah Model (20.12.2013)
  4. Segmentation II: Continuous Scaled Morphology, Shock Filters (09.01.2014)
  5. Segmentation III: Mean Curvature Motion (10.01.2014)
  6. Segmentation IV: Self-Snakes, Active Contours (17.01.2014)

PART 4: Pattern Recognition

  1. Pattern Recognition I: Basics, Terminology (23.01.2014)
  2. Pattern Recognition II: Bayes Decision Theory (24.01.2014)
  3. Pattern Recognition III: Parametric Techniques, Density Estimation (31.01.2014)
  4. Pattern Recognition IV: Non-Parametric Techniques (06.02.2014)
  5. Pattern Recognition V: Dimensionality Reduction (07.02.2014)



Files for the Programming Assignments

  1. Math Sheet (24.10.2013, no corresponding)
  2. Übung 1 (07.11.2013) (Programming Source)
  3. Übung 2 (21.11.2013) (Programming Source)
  4. Übung 3 (05.12.2013) (Programming Source)
  5. Übung 4 (19.12.2013) (Programming Source)
  6. Übung 5 (16.01.2014) (Programming Source)
  7. Übung 6 (30.01.2014) (Programming Source)



  1. Math Sheet (24.10.2013)
  2. Übung 1 (07.11.2013)
  3. Übung 2 (21.11.2013)
  4. Übung 3 (05.12.2013)
  5. Übung 4 (19.12.2013)
  6. Übung 5 (16.01.2014)
  7. Übung 6 (30.01.2014)



  • The programming exercises are designed for Linux. We only guarantee that the code works under Linux.
  • If possible, we will provide executables for Windows. You may use them at your own risk.
  • At some points we may have to provide object files for copyright reasons. Object files will only be provided for Linux.
  • If there are any problems reading in and writing out files under Windows, adding the binary flag may help, i.e. inimage = fopen(in,"rb");


Link zum LSF Online Portal:

Computer Vision

Übungen Computer Vision


Face reconstruction from a stereo pair.
Bild 1: Face reconstruction from a stereo pair.
Segmentation of a zebra and a frog.
Bild 2: Segmentation of a zebra and a frog.
Termine: Donnerstag, 14:00 - 15:30 Uhr (14-tägig) in V38.02
Freitag, 9:45 - 11:15 Uhr in 0.108
Übungen: Donnerstag, 14:00 - 15:30 Uhr (14-tägig) in V38.02
Tutor: Dipl.-Math. Sebastian Volz

« Zurück