Lectures are held in the building of UTIA CAS, Pod vodárenskou věží 4, Prague 8. Transportation: metro C, stop Ládví. Meet students in the lobby 10 minutes before the start of the class.

The exercises take place online on Zoom.

27.09. - 09:45 - lecture

04.09. - 09:45 - lecture

11.10. - 09:45 - lecture

18.10. - 09:45 - lecture

25.10. - 09:00 - labs ON-LINE

01.11. - 09:45 - lecture

08.11. - 09:45 - labs ON-LINE

15.11. - 09:45 - labs ON-LINE

22.11. - 09:45 - lecture

29.11. - 09:45 - labs ON-LINE

06.12. - 09:45 - labs ON-LINE

13.12. - 09:45 - labs

20.12. - 09:45 - labs

02.01. - 09:45 - labs

• Introduction to artificial intelligence, basic concepts

• Decision-making and recognition as an optimization problem

• Theory of feature recognition, "handcrafted" and "learned" features

• Intuitive classifiers with learning - NN classifier, k-NN classifier, linear classifier

• Support Vector Machines (SVM) classifiers, simple neural networks

• Bayesian approach to recognition

• Classification without learning - cluster analysis in the posterior of features, iterative and hierarchical methods

• Dimensionality reduction of the feature space, PCA, discriminant analysis

The files contain most of the slides used. This is not the complete lecture content; the knowledge recorded in the files is insufficient to pass the exam!

Always read the relevant part of [A] and, if possible, at least indicatively from [1] (Lectures 2,3,4) or [3] (Lecture 5).

[A] Introduction to Object Recognition. It contains many useful references for deeper study.

[1] Duda R.O. et al., Pattern Classification, (2nd ed.), John Wiley, New York, 2001

• An excellent textbook, covering in depth most of the lectures. Free download on several servers.

[2] Gonzales R. C., Woods R. E., Digital Image Processing (2nd ed.), Prentice Hall, 2002

• A good aid for exercises.

[3] Feature selection [CZ].

• Supplementary text to Lecture 5.

Will be published during the semester.

We are going to take a step into the world of Image Processing using python. In order to do that, you should know the basics of Python. Please go through the following section before attending labs. Necessary information for completing all labs will be provided here. If you have any questions please contact novozamsky@utia.cas.cz

The exercises will be in Czech, but all materials and texts will be in English.

Zoom account - the webcam will be on !

GitHub account

Gmail account for Colab is recommended

Browser

You should know:

• Python code structure, variables, functions, conditions, loops

• Containers: tuple, list, set, dict

• Object oriented programming

• Packages: Numpy, Matplotlib

At the beginning of every lab session, join Zoom Meeting, where you receive a link for a GitHub classroom assignment. It contains all codes for online/offline studying.

1. Zoom link: https://cuni-cz.zoom.us/j/91367957348

2. Get a link from your teacher, e.g. https://classroom.github.com/a/YspbK****

3. Sign in to GitHub

   • What is GitHub?

   • New to GitHub? Create an account.

   • Start using GitHub.

4. If necessary, click on the "Authorize GitHub Classroom" button

5. Find your name in the list (only for the first assignment)

6. Click on "Accept the assignment"

7. Go to colab.research.google.com

8. Click on "Authorize Google Colab"

9. Click on "GitHub" (or File > Open Notebook > GitHub)

10. Type your GitHub user name (check "Include private repos")

11. Find the desired repository and the notebook file

12. Loading (In case of "Error", press "Retry")

13. If necessary, click on the "Authorize with GitHub" button

14. Edit the notebook, finish excercises

15. Save in GitHub (File > Save a copy in GitHub)