The objective of this course is to learn and practice the basic methods of digital image analysis and pattern recognition: pre-processing, image segmentation, shape representation and classification
The course involves three lab sessions and a final capstone project. Concepts are illustrated by applications in computer vision and medical image analysis.
Official course description: https://edu.epfl.ch/coursebook/en/image-analysis-and-pattern-recognition-EE-451 Original lab notebooks are found in the official repository of the course: https://github.com/LTS5/iapr-2020
Team Members:
- Imad Eddine MAROUF
- Mert ERTUGRUL
- Arnaud DUVIEUSART
This lab is composed of two parts:
1- Brain tissue segmentation using a variety of region and contour based segmentation methods such as region growing, region splitting and merging, contour detection + binary region growing
2- Shape/color segmentation: counting the number of shapes of each color and computing the total area (in pixels) of each color.
This lab is composed of two parts:
1- Description of handwritten 0&1 using Fourier descriptors, PCA, t-SNE, Chamfer Distance and many other methods
2- Applying the same methods (a few key methods among them) to handwritten 0/1/2/3 to demonstrate how they perform for a larger number of different classes
Applying various classification methods such as Bayes method, KNN, MLP, CNN on data sets of three classes scattered on 2D space.
The detailed description and files of this project can be found in a repository in my fellow teammate Imad's profile: https://github.com/IemProg/IAPR_Project
- numpy
- scipy
- scikit-image
- matplotlib
- jupyter
- scikit-learn
- pandas
- seaborn
- torch
- opencv
- imageio
- tensorflow
- tqdm
- ffmpeg_python
- ffmpeg
- Pillow