• The date for the (oral) exams has been settled: Thursday, Sep 16, 09:00-11:00. The exam will be held at DFKI. The exact slots will follow.
  • The last lecture will be a guest lecture by Stephan Baumann on August 10 / 10:00-11:30 at DFKI(room “Bayes”/2.15)
  • The exam date will be settled with Prof. Dengel soon after Jul 20
  • The lecture this week (Jul 8) will be given at the regular time [WED 10:00] and place [42/110] by A. Ulges.
  • The current exercise sheet (number 4) is not to be handed in on May 26th (as stated on the sheet), but one week later (due to whitsun holidays). The next tutorial will be on June 2nd.
  • New location: lectures and tutorials on May 12th and May 19th will be shifted to DFKI!
    • tutorial/May 12th: DFKI building, room 2.17 (Bayes)
    • lecture/May 12th: DFKI building, room 2.17 (Bayes)
    • lecture/May 19th: DFKI building, room 1.15 (Pascal)
  • There *will* be a tutorial on April 28th! From this week on, tutorials will be given every second week.
  • The exams for this lecture will be held in oral form (more information on dates and organization will follow here).
  • The time slot for the exercises is settled to room 48/379, Wednesday 8:15-9:45 (same as in KIS). The first exercise on April 21st will cover the first exercise sheet (basic maths)
  • The lecture will start on April 14th. There will be *no* tutorials / exercises on April 14th!


lecture: room 42/110, Wednesday 10:00-11:30
tutorials: room 48/379, Wednesday 8:15-9:45

General Information

This lecture gives an introduction to models and algorithms underlying modern multimedia search technology. The focus will be on retrieving image and video content (though other media like text and audio will be touched as well).

  • Lecturers: Prof. Andreas Dengel, Dr. Adrian Ulges
  • Credits: 2C+1R, 4 credit points
  • Language: English
  • Level: Master (entry level)
  • Requirements
    • Introduction to Pattern Recognition (recommended, but not required)
    • Introduction to Image Processing and Image Understanding (recommended, but not required)
    • basic probability theory and analysis
  • Literature (available in computer science library):
    • Duda, Hart, Stork: Pattern Classification, 2nd edition
    • Gonzalez, Woods: Digital Image Processing
  • Exam: written or oral (to be discussed in class)
  • More information: see KIS / Modulhandbuch



Lecture schedule:

block lecturer content details slides exercise sheets & materials
1 Adrian Ulges introduction course formalities, definitions, history, lecture outline, introduction slides sheet
2 pattern recognition (supervised) basic decision theory, classification, classifier combination slides sheet material NumPy Website NumPy Tutorial
3 pattern recognition (unsupervised) clustering, dimensionality reduction slides sheet material
4 text retrieval document retrieval, retrieval models, relevance feedback, data structures slides
5 image representation I definitions, color spaces, features and their properties, invariance slides sheet material
6 image representation II local features: interest point detection, patch description, matching slides
7 similarity search I applications, prototypical architecture, distance measures, object search slides live exercise: pattern recognition user study
8 similarity search II scalability: kd-trees, locality-sensitive hashing slides
9 visual recognition I applications, challenges, face detection, face recognition, object recognition, visual words slides sheet material
10 visual recognition II object category recognition- SVMs, spatial constellation, research slides slides
11 visual recognition III concept detection and concept-based video retrieval, concept selection, research slides sheet material
12 video representation shot boundary detection, keyframe extraction, motion estimation, motion segmentation slides
13 Stephan Baumann music information retrieval audio features and meta features, categorization, recommendation (content-based vs collaborative), web mining, … slides

Last modified:: 19.08.2010