Print
Univis
Search
 
FAU-Logo
Techn. Fakultät Willkommen am Institut für Informatik FAU-Logo

Exercises

The exercise courses take place on:

Tuesdays 10:15 - 11:00 (02.134-113)

Wednesdays 14:15 - 15:00 (00.151-113)

Both courses 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 to Opens window for sending emailLennart Husvogt.

Start and Subscription

The exercise course starts on Tuesday (20.10.2015).

Welcome to the Exercises for Introduction to Pattern Recognition!

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. Exercise sheets will become available on this website.

Older lecture videos are available at Opens external link in new window (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 Python 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, or by request (write me an Opens window for sending emailemail).

 

In general, we advise you to use Python, which is available in the CIP pool including extensions such as OpenCV, but there are also other (open source) 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.

Assignments

Exercise Date of exercise session Sheet Solutions
1 Introduction20.10.2015 / 21.10.2015Initiates file downloadsheet01.pdfInitiates file download03_solution.py
2 Fourier Transform and Python27.10.2015 / 28.10.2015Initiates file downloadInitiates file downloadsheet02.pdfInitiates file download07_example.py
3 Fourier Series and SNR02.11.2015 / 03.11.2015

Initiates file downloadsheet03.pdf

Initiates file downloadsample.wav

Initiates file download09_solution.pdf

Initiates file download10_solution.py

4 k-Means Clustering and Histogram Equalization09.11.2015 / 10.11.2015

Initiates file downloadsheet04.pdf

Initiates file downloadLena.png

Initiates file downloadLenaLowContrast.png

Initiates file download11_solution.py
5 Image Filtering and Thresholds16.11.2015 / 17.11.2015Initiates file downloadsheet05.pdf
6 Edge Detection23.11.2015 / 24.11.2015

Initiates file downloadsheet06.pdf

Initiates file downloadmoon.jpg

Initiates file download18_solution.py

Initiates file download18 LaPlacian.v3.ipynb

Initiates file download18 LaPlacian.html

7 Simple Segmentation and Morphological Operations30.11.2015 / 01.12.2015

Initiates file downloadsheet07.pdf

Initiates file downloadbuoy.jpg

Initiates file download20_solution.py

Initiates file download20 Buoy Segmentation.v3.ipynb

Initiates file download20 Buoy Segmentation.html

8 Normalization with Moments07.12.2015 / 08.12.2015

Initiates file downloadsheet08.pdf

Initiates file downloadmomented.jpg

Initiates file download21_solution.py

Initiates file download21 Moments.v3.ipynb

Initiates file download21 Moments.html

9 Walsh Transform and 2D Frequency Domain Filtering14.12.2015 / 15.12.2015

Initiates file downloadsheet09.pdf

Initiates file downloadsaturn.jpg

Initiates file download23_solution.py

Initiates file download23 2D Frequency Domain Filtering.v3.ipynb

Initiates file download23 2D Frequency Domain Filtering.html

10 Frequency Domain Filtering II, LPC 21.12.2015 / 22.12.2015Initiates file downloadsheet10.pdf

Initiates file download25 Frequency Domain Filtering 2.v3.ipynb

Initiates file download25 Frequency Domain Filtering 2.html

11

Object Oriented Programming in Python

Note: the previous version of this sheet covered wavelet transforms which will be covered next week instead.

11.01.2016 / 12.01.2016Initiates file downloadsheet11.pdf

Initiates file download26_solution.py

Initiates file downloadfilter.py

12 Wavelets: A Compression Example18.01.2016 / 19.01.2016Initiates file downloadsheet12.pdf

Initiates file download27_solution.py

Initiates file downloadht.py

Initiates file download27 Wavelet Compression Example.v3.ipynb

Initiates file download27 Wavelet Compression Example.html

13 Eigenfaces25.01.2016 / 26.01.2016

Initiates file downloadsheet13.pdf

Initiates file downloadfaces.zip