Multimedia Computing and Computer Vision Lab












Student Theses


Source Code / Datasets




SS 10: Multimedia II: Media Mining

From Multimedia Computing Lab - University of Augsburg

Registration is open now! LectureReg


Instructors: Prof. Dr. Rainer Lienhart, Fabian Richter
Time Lecture: Tue, 10:00-11:30 and Thu, 12:15-13:45, room 1055 N
Time Exercise: Tue, 8:15-9:45, room 1054 N;
Please register with LectureReg
Examine: Thu, 10:00 - 12:00, Room: 1055 N, August, 5th 2010
Credits: 6 SWS, Schein: yes, LP: 9
Multimedia Teilbereiche: Multimedia-Methoden, Multimedia-Anwendungen
Synopsis: The course addresses all aspects of computer algorithms that let a computer see, hear, learn, and understand audio-visual and multimedia data in the small and large scale. Small scale refers to individual media files or streams, while large scale refers to mining the web.

Mining media data is inherently a multidisciplinary field. Thus, the course will lay down the foundations of

  • Machine learning,
  • Image/video processing, and
  • Media content analysis.

The learned concepts will be illustrated by successful examples in practice. The accompanying exercises will contain some hands-on experiences. Towards the end of the course more advanced topics in object detection and object recognition will be addressed.

Important Comments

  • In order to be admitted to the final exam, students are required to register with the course in LectureReg. No additional requirements are imposed.
  • All reading notes are relevant for the exams independent on how thoroughly they have been discussed during the lecture. Thus read them carefully.


  1. Mandatory reading: M. Mitchell. Machine Learning. McGraw-Hill Science/Engineering/Math; Chapters 1-8; (
  2. Mandatory reading: Jeff Hawkins, Sandra Blakeslee. On Intelligence. B&T; Auflage: Reprint (August 2005), ISBN-13: 978-0805078534
  3. Bernd Jähne. Digital Image Processing. Springer Verlag.
  4. David A. Forsyth and Jean Ponce. Computer Vision: A Modern Approach. Prentice Hall, Upper Saddle River, New Jersey 07458.( )


  1. Martin Schader and Stefan Kuhlins. Programmieren in C++. Springer-Verlag. ISBN 3540637761
    This is a perfect resource for all your questions relating C/C++; recommended if you are not skilled in C/C++
  2. Simon Hoffmann and Rainer Lienhart. OpenMP: Eine Einführung in die parallele Programmierung mit C/C++, Springer Verlag, April 2008, ISBN: 978-3-540-73122-1. (zur Verlagsseite)

Online Material

Date Content Slides Exercise Supplementary material
20.04. 1-01 Introduction PDF
22.04. 2-01 Introduction to Machine Learning PDF PDF, ZIP, Solution OpenCV Tutorial, Source Code
27/29.04. 2-02 Concept Learning PDF, PDF PDF
04/06.05. 2-03 Decision Tree Learning PDF PDF
06/11.05. 2-04 Artificial Neural Networks PDF PDF, Solution TrainData
18./20.05. 2-05 Evaluating Hypotheses PDF PDF
25.05./08.06. 2-06 Bayesian Learning PDF PDF, Solution ZIP1, ZIP2, ZIP3, ZIP4
10.06. 2-07 Computational Learning Theory PDF PDF
10./15.06 2-08 Instance Based Learning PDF PDF
17.06 2-09 Reinforcement Learning PDF PDF, PCA, NMF
22./29.06 3-01 Dimensionality Reduction Techniques PDF PDF
01./06.07 3-02 ShotDetection PDF PDF
08.07 3-03 Scene_and_Locale_Detection PDF
13.07 3-04 Commercial Detection PDF
13./20.7. 3-05 ObjectDetection PDF