• Lecturer: Jean-Philippe Thiran
• EE-451 coursebook
• Moodle

Learn the basic methods of digital image analysis and pattern recognition: pre-processing, image segmentation, shape representation and classification. These concepts will be illustrated by applications in computer vision and medical image analysis.

This repository contains the material for the labs and project associated with the EPFL master course EE-451 Image Analysis and Pattern Recognition.

Please find below the list of material accessible from this repository:

1. Installation instructions
2. Basic image processing tutorial
3. Lab 1: image segmentation

We will be using git, Python, and packages from the Python scientific stack. If you don't know how to install these on your platform, we recommend to install Anaconda or Miniconda, both are distributions of the conda package and environment manager. Please follow the below instructions to install it and create an environment for the course:

1. Download the latest Python 3.x installer for Windows, macOS, or Linux from https://www.anaconda.com/download or https://conda.io/miniconda.html and install with default settings. Skip this step if you have conda already installed (from Miniconda or Anaconda). Linux users may prefer to use their package manager.
   • Windows: Double-click on the .exe file.
   • macOS: Double-click on the .pkg file.
   • Linux: Run bash Anaconda3-latest-Linux-x86_64.sh in your terminal.
2. Open a terminal. For Windows: open the Anaconda Prompt from the Start menu.
3. Install git if not already installed with conda install git.
4. Download this repository by running git clone https://github.com/LTS5/iapr-2018.
5. It is recommended to create an environment dedicated to this course with conda create -n iapr2018 python=3.6.
6. Activate the environment:
   • Linux/macOS: source activate iapr2018.
   • Windows: activate iapr2018.
7. Install the packages we will be using for this course:
   • Linux/macOS: pip install --upgrade -r requirements.txt
   • Windows: conda install --file requirements.txt
8. You can deactivate the environment whenever you are done with deactivate

We suggest two different Python editors, but many more are available:

1. Jupyter is a very useful editor that run directly in a web browser. You can have Python and Markdown cells, hence it is very useful for examples, tutorials and labs. We encourage to use it for the lab assignments. To launch a Jupyter Notebook:
   • Open a terminal (for Windows open the Anaconda Prompt)
   • Activate the environment with source activate iapr2018 (For Windows: activate iapr2018)
   • Run the command: jupyter notebook.
2. PyCharm is an excellent Python IDE developed by JetBrains. It is more suitable for large projects than Jupyter, hence it might be useful for the final project. Multiple versions are available:
   • Free 'Community' version.
   • Professional version: free with the education pack (available for EPFL students).