Ertugrulmert / EPFL-Image-Analysis-and-Pattern-Recognition-Labs

Includes labs on the subjects of: Image Segmentation, Object Description, Classification

Repository from Github https://github.comErtugrulmert/EPFL-Image-Analysis-and-Pattern-Recognition-LabsRepository from Github https://github.comErtugrulmert/EPFL-Image-Analysis-and-Pattern-Recognition-Labs

EPFL: Image Analysis and Pattern Recognition Labs

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

Lab Descriptions

Lab 1: Image Segmentation:

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.

Lab 2: Object description:

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

Lab 3: Classification:

Applying various classification methods such as Bayes method, KNN, MLP, CNN on data sets of three classes scattered on 2D space.

Final Project:

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

Libraries Used

  • numpy
  • scipy
  • scikit-image
  • matplotlib
  • jupyter
  • scikit-learn
  • pandas
  • seaborn
  • torch
  • opencv
  • imageio
  • tensorflow
  • tqdm
  • ffmpeg_python
  • ffmpeg
  • Pillow

About

Includes labs on the subjects of: Image Segmentation, Object Description, Classification


Languages

Language:Jupyter Notebook 100.0%