Skip to content

Jooeys/CV-M2R-UGA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Working evvironment

Visual Studio Code - Insider Extension:Jupyter Virtual envrionment: Python3.7.9-64-bit ('cv-env':conda)

M2R - MSc in Informatics

Graphics Vision and Robotics and Ubiquitous Interface Systems

  • Computer Vision
  • MoSIG M2 2020-2021 Academic Year
  • ENSIMAG Amphi D - Thursdays 9:45 to 12:45
  • Professors: James L. Crowley and Edmond Boyer
  • Teaching Assistant: Nachwa Aboubakr

These class notes can be found at http://crowley-coutaz.fr/jlc/Courses/2020/GVR.VO/GVR-VO.html

The original planned Class schedule. Here is a pointer the the ADE class reservation system Programming Teams (as of 15 October).

Thursday 1 Oct 2020

Lesson 1: Theory: Performance Evaluation for Recognition and Detection Course Introduction: James Crowley

  • Course Organisation Computer Vision Theory: (Nachwa Aboubakr)
  • Pattern Recognition and Machine Learning
  • Performance Evaluation Evaluation Metrics Exercise Questions (exam questions from past years) Practical Instruction: Jupyter Notebooks, OpenCV, and FDDB.
  • Using OpenCV and Keras in Python with Jupyter Notebooks
  • Opening and displaying a face with the FDDB Data set

Programming Exercise 1: Displaying Faces from the FDDB data set Background Reading: The FDDB Data Base (Jain and Learned-Miller 2010)

Thursday 15 Oct 2020

Lesson 2: Visual Perception in Man and Machine (Recorded Lecture)

Computer Vision Theory (Recorded Lecture for Part 1)

  • Albedo and Reflectance
  • The Human Visual System
  • Vergence, Version and Fixation
  • Color Perception and Color Spaces Exercise Questions (exam questions from earlier years)

Practical Instruction (Recorded Lecture for Part 2)

  • Sliding Window Face Detectors
  • Programming Neural Networks in Keras
  • Detecting Faces with a 3 Layer MLP in Keras

Programming Exercise 2: Face Detection with a Multi-Layer Percetron Evaluation Data for Exercise 2 (from folds 9 and 10 of FDDB) Background Reading: (Rowley and Kanade 87)

Thursday 22 Oct 2020

Lesson 3: Scale Space and Image Pyramids (Recorded Lecture) Computer Vision Theory

  • Scale Space
  • Gaussian function as a low-pass digital filter
  • Scale Invariant Gaussian Pyramids
  • Equivariance Properties of Scale Space

Practical Instruction:

  • Constructing an Image pyramid with OpenCV
  • Detecting Faces at multiple scales with a pyramid

Programming Exercise 3: Detecting Faces at multiple scales with a pyramid and a sliding window MLP

Background Reading: Face Detection with Half octave Pyramid (Ruiz 2008) (Crowley-Riff 2003)