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

Slides

This material is copyrighted (c) 2014-2016 by Dr.-Ing. Stefan Steidl, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany. It is based on the former lectures Mustererkennung I & II by Prof. Dr.-Ing. Heinrich Niemann and the replacing lectures by Prof. Dr.-Ing. Joachim Hornegger and Elli Angelopoulou, PhD. Use without prior written permission of the authors is not permitted!

 

 

These slides are part of a presentation. The presentation is not complete without the verbal explanations given during the lecture.

The pdf files are password protected. You will get the password during the first lecture.

Three different versions of the slides are available:

  1. The 'screen' version are the slides presented during the lectures. They may contain embedded video and audio files leading to large file sizes. Furthermore, they use extensively overlays, i.e. slides are displayed incrementally, resulting in a sequence of pdf pages instead of a single one just showing the final outcome. Hence, this version is not suited for printing. The slides are best viewed with a software that is able to show overlays without transition effects (e.g. GoodReader for iPad).
  2. 'Print (A5)' shows two slides per page and is intended for printing booklets in the DIN A5 format. Let the printer driver rearrange the pages and use duplex printing. The printed versions do not contain video and audio files and most important, they do not have overlays. The printed versions include some slides that are especially designed for printing: for example, in a presentation, the difference between two similar images can be best viewed if both images are overlaid. As this is not possible in a print-out, both images are printed next to each other instead.
  3. 'Print (A6)' shows four slides per page. Besides the different arrangement of slides per page, the slides are identical to the other print version. This is the standard option for printing if you want to file your print-outs in a folder.

We will update the slides during the semester as needed in order to improve the quality of our slides.
Please make sure that you have the latest version of our slides in preparation for the exam!

 

 

Chapter Lecture

Slides

Date (Week) SlidesScreen
Print (A5)Print (A6) Update
1 Introduction 12.10.2015 (1) 1-1 - 1-43 pdfpdfpdf09.10.2015
2 Key concepts of pattern recognition14.10.2015 (1)2-1 - 2-20 pdfpdfpdf12.10.2015
19.10.2015 (2)2-21 - 2-38
3 Analog to digital conversion: sampling19.10.2015 (2)3-1 - 3-10 pdfpdfpdf26.10.2015
21.10.2015 (2)3-11 - 3-32
26.10.2015 (3)3-33 - 3-37
28.10.2015 (3)3-38 - 3-50
4 Analog to digital conversion: quantization28.10.2015 (3)4-1 - 4-19 pdfpdfpdf27.10.2015
02.11.2015 (4)4-20 - 4-30
5 Histogram equalization04.11.2015 (4)5-1 - 5-18 pdfpdfpdf02.11.2015
6 Thresholding and binarization04.11.2015 (4)6-1 - 6-30 pdfpdfpdf02.11.2015
09.11.2015 (5)
11.11.2015 (5)6-31 - 6-43
7 Filtering: noise suppression11.11.2015 (5)7-1 - 7-24 pdfpdfpdf11.11.2015
16.11.2015 (6)7-25 - 7-44
18.11.2015 (6)7-45 - 7-48
8 Edge detection18.11.2015 (6)8-1 - 8-44 pdfpdfpdf12.11.2015
9 Non-linear filtering23.11.2015 (7)9-1 - 9-18 pdfpdfpdf18.11.2015
25.11.2015 (7)9-19 - 9-56
10Normalization25.11.2015 (7)10-1 - 10-17 pdfpdfpdf23.11.2015
30.11.2015 (8)10-18 - 10-24
02.12.2015 (8)10-25 - 10-27
11Feature extraction: heuristic methods02.12.2015 (8)11-1 - 11-31 pdfpdfpdf09.12.2015
07.12.2015 (9)11-32 - 11-64
09.12.2015 (9)11-65 - 11-94
14.12.2015 (10)11-95 - 11-119
16.12.2015 (10)11-120 - 11-144
21.12.2015 (11)11-145 - 11-162
11.01.2016 (12)11-163 - 11-183
13.01.2016 (12)11-184 - 11-198
12Feature extraction: analytic methods13.01.2016 (12)12-1 - 12-4 pdfpdfpdf25.01.2016
18.01.2016 (13)12-5 - 12-20
20.01.2016 (13)12-21 - 12-41
25.01.2016 (14)12-42 - 12-65
13Numerical optimization04.02.2016 (15) 13-1 - 13-22 pdfpdfpdf17.12.2015
14Feature selection pdfpdfpdf17.12.2015
15Statistical classification27.01.2016 (14)15-1 - 15-42 pdfpdfpdf27.01.2016
16Polynomial classifier02.02.2016 (15)16-1 - 16-24 pdfpdfpdf01.02.2016
17Non-parametric classifiers04.02.2016 (15)17-1 - 17-31 pdfpdfpdf17.12.2015
18Kalman filter pdfpdfpdf17.12.2015

 

Link to last year's slides: IntroPR WS 2014/15

 

Additional material

Python code examples are shown during the lecture.
As we need OpenCV bindings, we stick to Python 2.7.10.
The algorithms are demonstrated using IPython Notebook.

Getting familiar with the algorithms is essential and will be part of the oral exams. This is especially true for the 7.5 ECTS exams. Please make sure that you have the latest version of the files as they are updated frequently.