Techn. Fakultät Willkommen am Institut für Informatik FAU-Logo


One of our test images for blurring and image noise.
One of our test images for sharpening.

Welcome to the Exercises for Introduction to Pattern Recognition!

The exercises start in the second week of the winter term. Most of the time, Opens internal link in current windowChristian Riess will hold the exercises. The topics are relatively closely related to the lecture. We will have theoretical exercises, where we aim to deepen our understanding of elements within the pattern recognition pipeline. Additionally, we have practical tasks, in order to observe the behavior of the methods on real-world data.

Please choose one of the two exercise sessions, either on Wednesday, 16:15-17:00h in room 09.150 (seminar room of the Pattern Recognition Lab) or on Thursday, 11:00-11:45h in room E 1.12 (seminar room in the Electrical Engineering building).

A single session will typically take only 45 minutes. We will discuss the precise start and end time in the first meeting.


The lecture video is available Opens external link in new windowhere (only accessible if you are inside the university network; if you want to watch the videos from home, consider to tunnel the connection).


Note: on Thursday, February 7th, we are in room E 1.12 (same location as always, just on the opposite side of the floor).

Work Sheets

  • Initiates file downloadExercise 1 - we start (with the first exam question).
  • Initiates file downloadExercise 2 - ML Estimation and Thresholding. Note that we do only programming-related tasks in the week of Nov. 7th and Nov. 8th, the ML Estimation will be done one week later. By the way, here is a test image for the programming task in this exercise: Initiates file downloadobject. NOTE: There was an issue viewing the first version of the document in acroread. This has been fixed.
  • Initiates file downloadExercise 3 - Image enhancement and interpolation artifacts. We have a couple of programming tasks in this exercise. You can use the Initiates file downloadmoon image as an input for the Laplacian filter.
  • Initiates file downloadExercise 4 - We examine the difference between band limited Fourier series and the analytical (exact) solution. Additionally, we implement Histogram equalization, and discuss tricks to extend the basic (gray scale) algorithm to color images. For testing, you can use the two low-contrast versions of the Lena images Initiates file downloadhere and Initiates file downloadhere.
  • Initiates file downloadExercise 5 - small repetition on moments. Additionally, we have a look at the Welsh transform and on linear predictive coding. The test image "momented" is Initiates file downloadhere.
  • Initiates file downloadExercise 6 - Haar Wavelets. We examine the capabilities of wavelets within an example for image compression. For testing, you can use this Initiates file downloadblack and white Lena image.
  • Initiates file downloadExercise 7 - PCA! One full work sheet packed with example calculations and a programming task for this important technique. Maybe you would also like to think about the 'bonus' part at the end of the work sheet. The data file for matlab is Initiates file downloadhere, for all other languages Initiates file downloadhere and Initiates file downloadhere.
  • Initiates file downloadExercise 8 - feature selection using the branch-and-bound search algorithm. Note the last question: where in the whole pipeline should feature selection be performed?
  • Initiates file downloadExercise 9 - optimal classification, and a polynomial classifier for 'straightforward' classification tasks. Note that polynomial classifiers are not the end of history: trickier classifiers are presented in the lecture "Pattern Recognition".