Multimedia Computing and Computer Vision Lab












Student Theses


Source Code / Datasets




WS 14/15: Seminar: Multimediale Datenverarbeitung

From Multimedia Computing Lab - University of Augsburg

Please use the DigiCampus page to sign up for this seminar. Registration will be opened on 06.10.2014.

Homography estimation with RANSAC
Canny Edge Detector
Segmentation with Quickshift


Course Title: Seminar: Multimedia Computing (B.S.), Bachelor
Advisors: Prof. Dr. Rainer Lienhart, Christian Eggert
Kick-off event: Thursday, 06. Nov. 2013, 14:00 - 15:00, Room 1021 N
Papers due: Sat, 28. Feb. 2014 23:59
Credits: 2 SWS, 4 LP
Examination: Term paper (approx. 10 pages) and presentation (25 minutes + 5-10 minutes discussion). Attendance during the presentation of the other students is required.
Language: German, English
Max. participants 12
Summary: In this seminar we will discuss algorithms and techniques from the area of computer vision and machine learning.

Appointments and dates

Date Topic / Event
06.11.2014 Introduction / Topic presentation
07.12.2014 Outline due date
11.01.2015 First draft due date
08.02.2015 Last date for pre-submission paper review
28.02.2015 Final paper submission deadline

Examination details

  • Presentation: approx. 25 minutes with 5-10 minutes of discussion
  • Term paper: approx: 10 pages
  • Attendance during the presentations
  • Grading: 60% Paper, 40% Presentation

Additional info and materials

  • Presentation and term paper either in German or English
  • For those who want to use Latex we offer a template which is available for download through DigiCampus
  • Programming knowledge is not required. However, we do appreciate small demo programs during the presentation


The following topics are available. You will be able to pick your preferred topics during the kick-off meeting. We will then assign the topics based on your preferences.

We offer topics from three different areas:

Image Features

  • Scale-invariant feature transform (SIFT)
  • Speeded up Robust Features (SURF)
  • Local Intensity Order Pattern (LIOP)
  • Maximally stable extremal Regions (MSER)


  • Edge detection with Canny
  • Nearest neighbor search with FLANN
  • Homography estimation with RANSAC
  • Image segmentation with Quickshift

Machine Learning

  • AdaBoost
  • Artificial Neural Networks
  • Random Forests
  • Support Vector Machines (SVMs)


Date Action
22. Sep 2014 Page creation
06. Nov 2014 Updated: Dates and Events