Digital Imaging / Visual Computing 2023
This is the repository for the Digital Imaging / Visual Computing course (05_DVC4IL) at the FH Hagenberg.
Contact: David C. Schedl.
Tutorials:
| # | Tutorial (link to .ipynb) |
Open in Colab |
|---|---|---|
| 1 | Python for Computer Vision |  |
| 2 | Introduction to OpenCV | |
| 3 | Histograms | |
| 4 | Filters | |
| 5 | Edges | |
| 6 | Thresh | |
| 7 | Lines | |
| 8 | ML | |
| 9 | NN | |
| 101 | CNN | |
| 11 | Transfer Learning | |
| 12 | Object Detection | |
Homework Tasks:
| # | Homework (link to .ipynb) |
Open in Colab |
|---|---|---|
| 1 | Point Operations and Histograms | |
| 2 | Hybrid Images | |
| 3 | Binary Leaves | |
| 4 | Image Classification | |
Python Setup:
Students have the option to run the code online with Google Colab (requires a Google account) or locally with your own installation of Python.
Online:
Everything runs on a Google machine, so you don't need to set up anything on your computer. Furthermore, the machines come with the most popular libraries preinstalled.
Just click on the corresponding Open in Colab badge:
Local:
Install Python on your computer via Conda/Miniconda or the Python Installer. Use Python3, as Python2 is not supported anymore. Furthermore, you need an Editor that supports Jupyter (.ipynb) notebooks. I recommend using Visual Studio Code. Optionally, you can also use a local server and open Notebooks in your browser (Visual Studio simplifies this).
Useful Links:
- Python Documentation
- OpenCV Tutorial
- If you know Matlab, you can find the differences between Matlab and Python here.
Course Grading:
This course will be graded based on your performance in the course homeworks. The homework tasks will be announced while we progress through the course.
Footnotes
-
Using Colab is highly recommended for these tutorial(s). ↩