Multimedia Computing and Computer Vision Lab

Login  

Home

     

Courses

     

People

     

Research

     

Publications

     

Student Theses

     

Source Code / Datasets

     

Contact

     

SS 11: Multimedia II: Media Mining

From Multimedia Computing Lab - University of Augsburg


Registration is open now! LectureReg

Overview

Instructors: Prof. Dr. Rainer Lienhart, Thomas Greif
Time Lecture: Tue, 10:00-11:30 and Fri, 08:15-09:45, room 1055 N
Time Exercise: Fri, 12:15-13:45, room 1057 N;
Please register with LectureReg
Exam: Friday, August 5, 2011, 12:00 - 14:00, rooms: 1057 N and 1058 N
Credits: 6 SWS, LP: 8
Multimedia Teilbereiche: Multimedia-Methoden, Multimedia-Anwendungen
Synopsis: This course addresses state-of-the-art computer vision algorithms that let computers see, learn, and understand image and video content. After being taught the required basics in machine learning, students will - accompanied by practical exercises - get to know the most promising techniques.

The topics of the course may be summarized as follows:

  • Machine learning
  • Image/video processing
  • 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.

News

  • [12.04.2011] Page creation.

Important Comments

  • In order to be admitted to the final exam, students are required to register with the course in LectureReg and STUDIS. 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.

Literature

  1. M. Mitchell. Machine Learning. McGraw-Hill Science/Engineering/Math; Chapters 1-8; (http://www-2.cs.cmu.edu/~tom/mlbook.html)
  2. 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.( http://www.cs.berkeley.edu/~daf/book.html )
  5. Martin Schader and Stefan Kuhlins. Programmieren in C++. Springer-Verlag. ISBN 3540637761
  6. 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
03.05. 1-01 Introduction PDF

Machine Learning
06.05. 2-01 Introduction to Machine Learning PDF PDF ZIP
10.05. 2-02 Concept Learning PDF PDF
13.05. 2-03 Decision Tree Learning PDF PDF
17./20.05. 2-04 Artificial Neural Networks PDF PDF
24.05. 2-05 Evaluating Hypotheses PDF PDF
26./31.05.
03.06.
2-06 Bayesian Learning PDF PDF ZIP1, ZIP2, ZIP3, ZIP4, ZIP
07./10.06. 2-07 Computational Learning Theory PDF PDF
10.06. 2-08 Instance Based Learning PDF PDF

Data Reduction
17./21.06. 3-01 Quantization PDF PDF
21./24.06 3-02 Dimensionality Reduction Techniques PDF PDF

Computer Vision
01./05.07. 4-01 Feature Detectors PDF PDF
05./08.07. 4-02 Feature Descriptors and Feature Matching PDF PDF
12./15./18.07. 4-03 ObjectDetection
  • Neutral Networks (Rowley)
  • Cascade of Boosted Classifiers (Viola)
  • Pictorial Structures (Felzenszwalb)
PDF
PDF
Object Detection with Discriminatively Trained Part Based Models
22./25.07. 4-04 Image Search with pLSA PDF
PDF
29.07. Q & A
</div>