Print
Univis
Search
 
FAU-Logo
Techn. Fakultät Website deprecated and outdated. Click here for the new site. FAU-Logo

Exercises

The exercise courses will be held on:

Mondays 08:45 - 09:30 (00.151-113)
Mondays 10:15 - 11:00 (02.134-113)

Both courses will cover the same topics.

If there are any questions or problems regarding the exercises that could not be clarified within the courses, feel free to come by or write an Opens window for sending emailemail to Simone or Opens window for sending emailOliver.

Start and Subscription

As the blue building is still closed, the exercises will start October 20, 2014. Instead of 45 minutes, the first exercise will then probably take a bit longer (estimated: 60-75 minutes).

Any information regarding the exercises and the assignments will be given in the first lecture or exercise.

Welcome to the Exercises for Introduction to Pattern Recognition!

Most of the time, Opens internal link in current windowSimone Gaffling 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.

 

Both exercise sessions cover the same content. A single session will typically take about 45-60 minutes.

Older lecture videos 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). Be aware that the contents of the lecture have changed since then!

 

Some remarks about programming


We will shortly go over the (Matlab) code for the practical exercises in the sessions. The solutions will be provided (password-protected) after another week. The password will be announced in the next sessions (week Oct. 27 - Oct. 31), or by request (write me an Opens window for sending emailemail).

 

In general, we advise you to use Matlab (available in CIP-Pool, all toolboxes available, support can be offered, nice tutorials online (e.g., Opens external link in new windowthis one), Initiates file downloadLME-Matlab-demo), but there are also other (OpenSource) possibilities:

 

- Opens external link in new windowWeka toolbox: Only for feature vectors, cannot handle images. Java-based. To extract features you might in some cases use:

- Opens external link in new windowFiji: General useful image processing tool with a lot of functionality (provided by research institutions based on plugins)

- Opens external link in new windowInsightToolkit (ITK): C++ based, more Image Processing and less pattern recognition.

- Opens external link in new windowOpenCV (CV = Computer Vision): C++-based. More pattern recognition/computer vision than image processing (basics are available, though). Nice examples, like tracking, included.

 

If using ITK and/or OpenCV, you can use the free express-editions of Visual Studio (google for download links).

In case of questions, contact me.

News

  • 03.11.14
    The exercise session on Nov 3 is cancelled due to illness!
  • 05.11.14
    To compensate the missed exercise session, the sessions on monday, Nov 10 will be:
    - 8:15 - 9:45
    - 10:15 - 11:45

Assignments

Exercise Date of exercise session Sheet Solutions
1 Introduction20.10.2014Initiates file downloadEx1.pdf
2 Quantization, SNR27.10.2014Initiates file downloadEx2.pdf (updated)
Initiates file downloadkMeans.zip
3 Fourier Transform, Histogram Equalization03.11.2014Initiates file downloadEx3.pdf, Initiates file downloadaudio2.wav (updated 30.11.), Initiates file downloadLenaRGB.png,Initiates file download LenaLowContrast.pngInitiates file downloadSolutions
4 Filtering, Convolution, Binarization10.11.2014Initiates file downloadEx4.pdf (updated 7.11.), Initiates file downloadobject.png, Initiates file downloadmask.pngInitiates file downloadSolutions
5 Image Enhancement, Normalization17.11.2014Initiates file downloadEx5.pdf, Initiates file downloadHistoimages.zipInitiates file downloadSolutions
6 Image Moments24.11.2014Initiates file downloadEx6.pdf, Initiates file downloadimages_moments.zipInitiates file downloadSolution
7 Walsh Transform, Fourier Domain Processing01.12.2014Initiates file downloadEx7.pdf, Initiates file downloadsaturn.tifInitiates file downloadSolution
8 Fourier Domain Processing II, LPC08.12.2014Initiates file downloadEx8.pdf (sorry for the delay), Initiates file downloadbasisprogram.mInitiates file downloadSolution
9 Wavelet Compression15.12.2014Initiates file downloadEx9.pdfInitiates file downloadSolution
10 PCA12.01.2015Initiates file downloadEx10.pdf, Initiates file downloadpca_data.matInitiates file downloadSolution
11 Nonlinear Optimization19.01.2015Initiates file downloadEx11.pdf, Initiates file downloadrosenbrock.zipInitiates file downloadSolution
12 Polynomial Classifier, Branch-and-Bound26.01.2015Initiates file downloadEx12.pdfInitiates file downloadSolution