Syllabus 2017 - 2018
====================

Objectives
----------

After you have succesfully followed the course on image processing and
computer vision you will be able to use techniques to process and
analyze images.

In this course we will introduce the basic notions in image processing
and computer vision in such a way that a student will be able to use
them for practical purposes *and* have an understanding of the
theoretical (mathematical) basics.

Algorithms for image processing and computer vision are often the
'materialization' of mathematical formula's. Being able to make a
program from a mathematical description using the Python programming
language and Numpy/Scipy packages is an important objective of this
course.

A student that followed the course succesfully should:

- be able to apply relatively simple methods to analyze images
  in practical settings, and
- be prepared for a master level course on computer vision.


Contents
--------

- Image Representation

- Color

- Point Operators

- Geometrical Operators

- Local Operators

  - Linear Operators (convolutions)

  - Morphological Operators (dilation and erosions)


- Local Structure

  - 2D Taylor Series

  - Gaussian Derivatives

  - Geometrical Invariants

  - Histogram of Gradients


- Scale Space

  - Linear Scale Space

  - Extrema in scale space

- Image Stitching Application

  - SIFT

  - RANSAC


- The Pinhole Camera

  - Projective Geometry

  - Pinhole Camera Calibration


- Motion

  - Optic Flow

  - Normalized Cross Correlation

    

  
Recommended Prior Knowledge
---------------------------

Linear algebra, calculus, machine learning, programming in Python/Numpy.



Teaching Staff
--------------

:Lecturers:
   
   - Rein van den Boomgaard,  Room C3.139, rvdboomgaard@gmail.com
     
:Teaching Assistents: 

   - Casper Gyurik, BSc
   - Daan Kruis
   - Govert Verkes, BSc



Format
------

- Lectures on Tuesdays and Wednesdays
- Tutor session on Friday
- Lab Sessions on Tuesdays and Fridays

Note that both lectures and tutor sessions are indicated as "werkcolleges" in datanose.
  

Study Materials
---------------

- Lecture Notes (https://staff.fnwi.uva.nl/r.vandenboomgaard/IPCV20162017) including the LabExercises.
- Web resources (refered to in lecture notes).
- Scientific articles (tba and refered to in lecture notes).
- Previous exams


Assessment
----------

- LabExercises 30%
- Exam  70% 


The minimal required grade for the LabExercises and the Final Exam is
5. Note that although you do get credit for the LabExercises these
exercises are not meant to really grade your work (you can probably
find similar work on the web.. or copy from someone else.. or let your
partner do all the work, or...). Lab exercises are meant to help you
understand the concepts discussed in the lectures and to prepare for
the exams. The final exam is the ultimate test. Be prepared for
questions in the final exam regarding the work done in the lab
exercises.